#966 by GitHub stars
unbrowse-ai/unbrowse
Unbrowse - Reverse engineer any website so that your agents can access its APIs directly
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
plugins/claude-code/skills/unbrowse/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → e8f5f04b761a
No earlier version was observed for comparison.
plugins/codex/skills/unbrowse/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → e8f5f04b761a
No earlier version was observed for comparison.
plugins/cursor/skills/unbrowse/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → e8f5f04b761a
No earlier version was observed for comparison.
plugins/elizaos/skill/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → e8f5f04b761a
No earlier version was observed for comparison.
plugins/grok-build/skills/unbrowse/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → e8f5f04b761a
No earlier version was observed for comparison.
plugins/hermes/skills/unbrowse/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → e8f5f04b761a
No earlier version was observed for comparison.
plugins/openclaw/skills/unbrowse/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → e8f5f04b761a
No earlier version was observed for comparison.
skill/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → e8f5f04b761a
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit e8f5f04b761a1ab64f7c1c93fea3552c0de5c813
git clone --filter=blob:none --no-checkout https://github.com/unbrowse-ai/unbrowse.git .hotskills/unbrowse-ai-unbrowse && git -C .hotskills/unbrowse-ai-unbrowse checkout --detach e8f5f04b761a1ab64f7c1c93fea3552c0de5c813
# Copy each selected skill directory from .hotskills/unbrowse-ai-unbrowse into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/unbrowse-ai/unbrowse.git .hotskills/unbrowse-ai-unbrowse && git -C .hotskills/unbrowse-ai-unbrowse checkout --detach e8f5f04b761a1ab64f7c1c93fea3552c0de5c813
# Copy each selected skill directory from .hotskills/unbrowse-ai-unbrowse into .agents/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/unbrowse-ai/unbrowse.git .hotskills/unbrowse-ai-unbrowse && git -C .hotskills/unbrowse-ai-unbrowse checkout --detach e8f5f04b761a1ab64f7c1c93fea3552c0de5c813
# Copy each selected skill directory from .hotskills/unbrowse-ai-unbrowse into .gemini/skills/<skill-name>/904GitHub stars
86stars in 7 days
8skills in this repository
41commits in 30 days
Heat
8.0- Star growth, last 7 daysAhead of 98% of tracked repositories
- Star growth, last 24 hoursAhead of 93% of tracked repositories
- Rank movement, last 7 daysNot available
- Commits, last 30 daysAhead of 89% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
How it works
unbrowse
When your agent uses it
Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser. Use for structured website tasks, and authenticated site access with Unbrowse.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
4,134 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Onboarding: sign in with OAuth
- Host plugins
- Choose the interface
- Execute a task
- Unbrowse a URL
- A site's tools over plain HTTP
- Read or learn a site
- Bring the agent's MCP servers
- Website sign-in
- Serving many users (orgs)
- Limits and recovery
Files
../../../../.claude-plugin/marketplace.jsonasset426 bytes../../.claude-plugin/plugin.jsonasset532 bytes../../hooks/hooks.jsonasset664 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesreferences/tools.jsonasset36,509 bytes../../../codex/hooks/hooks.jsonasset639 bytes../../../codex/hooks/hooks.jsonasset639 bytes../../../codex/hooks/hooks.jsonasset639 bytes../../../grok-build/hooks/hooks.jsonasset322 bytes../../../grok-build/hooks/hooks.jsonasset322 bytes
Read SKILL.md
# Unbrowse
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below.
## Onboarding: sign in with OAuth
Sign-in is OAuth in the person's browser: an emailed sign-in link, then **Allow**. No password, and nothing to paste. Never ask the person for a token or key in chat.
Check first, then sign in only what is missing:
1. MCP: if `unbrowse_discover` is in this session's tool list, the MCP is signed in.
2. CLI: `npx unbrowse whoami`. Exit 0 means signed in. Exit 3 means not signed in.
Sign in the MCP (agent hosts):unbrowse
When your agent uses it
Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser. Use for structured website tasks, and authenticated site access with Unbrowse.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
4,134 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Onboarding: sign in with OAuth
- Host plugins
- Choose the interface
- Execute a task
- Unbrowse a URL
- A site's tools over plain HTTP
- Read or learn a site
- Bring the agent's MCP servers
- Website sign-in
- Serving many users (orgs)
- Limits and recovery
Files
SKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesreferences/tools.jsonasset36,509 bytes
Read SKILL.md
# Unbrowse
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below.
## Onboarding: sign in with OAuth
Sign-in is OAuth in the person's browser: an emailed sign-in link, then **Allow**. No password, and nothing to paste. Never ask the person for a token or key in chat.
Check first, then sign in only what is missing:
1. MCP: if `unbrowse_discover` is in this session's tool list, the MCP is signed in.
2. CLI: `npx unbrowse whoami`. Exit 0 means signed in. Exit 3 means not signed in.
Sign in the MCP (agent hosts):unbrowse
When your agent uses it
Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser. Use for structured website tasks, and authenticated site access with Unbrowse.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
4,134 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Onboarding: sign in with OAuth
- Host plugins
- Choose the interface
- Execute a task
- Unbrowse a URL
- A site's tools over plain HTTP
- Read or learn a site
- Bring the agent's MCP servers
- Website sign-in
- Serving many users (orgs)
- Limits and recovery
Files
SKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesreferences/tools.jsonasset36,509 bytes
Read SKILL.md
# Unbrowse
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below.
## Onboarding: sign in with OAuth
Sign-in is OAuth in the person's browser: an emailed sign-in link, then **Allow**. No password, and nothing to paste. Never ask the person for a token or key in chat.
Check first, then sign in only what is missing:
1. MCP: if `unbrowse_discover` is in this session's tool list, the MCP is signed in.
2. CLI: `npx unbrowse whoami`. Exit 0 means signed in. Exit 3 means not signed in.
Sign in the MCP (agent hosts):unbrowse
When your agent uses it
Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser. Use for structured website tasks, and authenticated site access with Unbrowse.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
4,134 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Onboarding: sign in with OAuth
- Host plugins
- Choose the interface
- Execute a task
- Unbrowse a URL
- A site's tools over plain HTTP
- Read or learn a site
- Bring the agent's MCP servers
- Website sign-in
- Serving many users (orgs)
- Limits and recovery
Files
SKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesreferences/tools.jsonasset36,509 bytes
Read SKILL.md
# Unbrowse
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below.
## Onboarding: sign in with OAuth
Sign-in is OAuth in the person's browser: an emailed sign-in link, then **Allow**. No password, and nothing to paste. Never ask the person for a token or key in chat.
Check first, then sign in only what is missing:
1. MCP: if `unbrowse_discover` is in this session's tool list, the MCP is signed in.
2. CLI: `npx unbrowse whoami`. Exit 0 means signed in. Exit 3 means not signed in.
Sign in the MCP (agent hosts):unbrowse
When your agent uses it
Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser. Use for structured website tasks, and authenticated site access with Unbrowse.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
4,134 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Onboarding: sign in with OAuth
- Host plugins
- Choose the interface
- Execute a task
- Unbrowse a URL
- A site's tools over plain HTTP
- Read or learn a site
- Bring the agent's MCP servers
- Website sign-in
- Serving many users (orgs)
- Limits and recovery
Files
SKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesreferences/tools.jsonasset36,509 bytes
Read SKILL.md
# Unbrowse
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below.
## Onboarding: sign in with OAuth
Sign-in is OAuth in the person's browser: an emailed sign-in link, then **Allow**. No password, and nothing to paste. Never ask the person for a token or key in chat.
Check first, then sign in only what is missing:
1. MCP: if `unbrowse_discover` is in this session's tool list, the MCP is signed in.
2. CLI: `npx unbrowse whoami`. Exit 0 means signed in. Exit 3 means not signed in.
Sign in the MCP (agent hosts):unbrowse
When your agent uses it
Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser. Use for structured website tasks, and authenticated site access with Unbrowse.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
4,134 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Onboarding: sign in with OAuth
- Host plugins
- Choose the interface
- Execute a task
- Unbrowse a URL
- A site's tools over plain HTTP
- Read or learn a site
- Bring the agent's MCP servers
- Website sign-in
- Serving many users (orgs)
- Limits and recovery
Files
SKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesreferences/tools.jsonasset36,509 bytes
Read SKILL.md
# Unbrowse
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below.
## Onboarding: sign in with OAuth
Sign-in is OAuth in the person's browser: an emailed sign-in link, then **Allow**. No password, and nothing to paste. Never ask the person for a token or key in chat.
Check first, then sign in only what is missing:
1. MCP: if `unbrowse_discover` is in this session's tool list, the MCP is signed in.
2. CLI: `npx unbrowse whoami`. Exit 0 means signed in. Exit 3 means not signed in.
Sign in the MCP (agent hosts):unbrowse
When your agent uses it
Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser. Use for structured website tasks, and authenticated site access with Unbrowse.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
4,134 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Onboarding: sign in with OAuth
- Host plugins
- Choose the interface
- Execute a task
- Unbrowse a URL
- A site's tools over plain HTTP
- Read or learn a site
- Bring the agent's MCP servers
- Website sign-in
- Serving many users (orgs)
- Limits and recovery
Files
SKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesreferences/tools.jsonasset36,509 bytes
Read SKILL.md
# Unbrowse
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below.
## Onboarding: sign in with OAuth
Sign-in is OAuth in the person's browser: an emailed sign-in link, then **Allow**. No password, and nothing to paste. Never ask the person for a token or key in chat.
Check first, then sign in only what is missing:
1. MCP: if `unbrowse_discover` is in this session's tool list, the MCP is signed in.
2. CLI: `npx unbrowse whoami`. Exit 0 means signed in. Exit 3 means not signed in.
Sign in the MCP (agent hosts):unbrowse
When your agent uses it
Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser. Use for structured website tasks, and authenticated site access with Unbrowse.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
4,134 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Onboarding: sign in with OAuth
- Host plugins
- Choose the interface
- Execute a task
- Unbrowse a URL
- A site's tools over plain HTTP
- Read or learn a site
- Bring the agent's MCP servers
- Website sign-in
- Serving many users (orgs)
- Limits and recovery
Files
SKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesSKILL.mdcore16,889 bytesreferences/tools.jsonasset36,509 bytes
Read SKILL.md
# Unbrowse
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below.
## Onboarding: sign in with OAuth
Sign-in is OAuth in the person's browser: an emailed sign-in link, then **Allow**. No password, and nothing to paste. Never ask the person for a token or key in chat.
Check first, then sign in only what is missing:
1. MCP: if `unbrowse_discover` is in this session's tool list, the MCP is signed in.
2. CLI: `npx unbrowse whoami`. Exit 0 means signed in. Exit 3 means not signed in.
Sign in the MCP (agent hosts):Skills included
- unbrowse
- unbrowse
- unbrowse
- unbrowse
- unbrowse
- unbrowse
- unbrowse
- unbrowse
Repository facts
- License
- MIT
- Created
- Jan 27, 2026
- Last pushed
- Nov 3, 2026
- Forks
- 80
- Open issues
- 2
- Project activity
- Active
Rank over the last 12 weeks
Now #966 · best #660 · down 151 in 30 days
- #808 on Oct 24
- #994 on Oct 25
- #993 on Nov 2
- #988 on Nov 3
- #970 from Nov 4 to Nov 5
- #966 since Nov 6
45 earlier periods
- #757 on Aug 1
- #691 on Aug 6
- #684 on Aug 14
- #660 on Aug 15
- #688 on Aug 17
- #704 on Aug 18
- #689 on Aug 19
- #668 on Aug 22
- #695 on Aug 23
- #717 on Aug 26
- #725 on Aug 27
- #751 on Aug 28
- #690 on Aug 29
- #733 on Aug 31
- #747 on Sep 1
- #733 on Sep 2
- #732 on Sep 6
- #739 on Sep 12
- #740 on Sep 13
- #777 on Sep 21
- #797 on Sep 22
- #767 on Sep 27
- #790 on Sep 28
- #817 on Sep 29
- #802 on Sep 30
- #751 on Oct 1
- #753 on Oct 3
- #781 on Oct 4
- #792 on Oct 5
- #797 on Oct 6
- #815 on Oct 7
- #855 on Oct 8
- #816 on Oct 9
- #798 on Oct 10
- #800 on Oct 11
- #821 on Oct 12
- #827 on Oct 13
- #839 on Oct 14
- #825 on Oct 15
- #833 on Oct 16
- #808 on Oct 17
- #795 on Oct 18
- #840 on Oct 19
- #864 on Oct 21
- #851 on Oct 23
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 27 notes
plugins/claude-code/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/claude-code/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/claude-code/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/grok-build/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/codex/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/cursor/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/cursor/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/cursor/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/elizaos/skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/elizaos/skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/elizaos/skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/grok-build/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/grok-build/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/grok-build/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/hermes/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/hermes/skills/unbrowse/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 272 network referencesin 18 files: unbrowse/references/tools.json:1 unbrowse/references/tools.json:1 unbrowse/references/tools.json:1 and 15 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 24 references to secretsin 16 files: unbrowse/references/tools.json:188 unbrowse/references/tools.json:188 unbrowse/references/tools.json:188 and 13 more
- No requests to vote in Hot
Show all 296 signals by file
.claude-plugin/marketplace.json
- Network accessline 1
{ "name": "unbrowse", "owner": { "name": "Unbrowse", "url": "https://unbrowse.ai" }, - Network accessline 2
"name": "unbrowse", "owner": { "name": "Unbrowse", "url": "https://unbrowse.ai" }, "metadata": { "description": "Unbrowse plugins: websites as APIs for coding agents." }, - Network accessline 3
"owner": { "name": "Unbrowse", "url": "https://unbrowse.ai" },
plugins/claude-code/.claude-plugin/plugin.json
- Network accessline 4
"version": "12.5.0", "description": "Websites as APIs for Claude Code: the hosted Unbrowse MCP (discover, run, scrape, cloud browser, saved logins) plus its skill. Replaces WebFetch, WebSearch and browser MCPs with Unbrowse.", "author": - Network accessline 5
"description": "Websites as APIs for Claude Code: the hosted Unbrowse MCP (discover, run, scrape, cloud browser, saved logins) plus its skill. Replaces WebFetch, WebSearch and browser MCPs with Unbrowse.", "author": { "name": "Unbrowse", - Network accessline 6
"author": { "name": "Unbrowse", "url": "https://unbrowse.ai" }, - Network accessline 7
"homepage": "https://unbrowse.ai", - Network accessline 8
"repository": "https://github.com/unbrowse-ai/unbrowse",
plugins/claude-code/skills/unbrowse/SKILL.md
- Network accessline 8
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below. - Network accessline 22
claude mcp add --transport http unbrowse https://unbrowse.ai/mcp - Network accessline 26
{"mcpServers":{"unbrowse":{"url":"https://unbrowse.ai/mcp"}}} - Network accessline 37
`unbrowse login` opens the sign-in page in the browser on this machine. The person enters their email, opens the link, presses **Allow**; the CLI prints `Signed in to https://unbrowse.ai (workspace ws_…)` and stores the token at `~/.config/ - Network accessline 39
From an agent's shell (no terminal for the person): run `npx unbrowse login --no-open` in the background, give the person the `https://unbrowse.ai/authorize?…` link it prints, and wait for the `Signed in` line. The link returns to `127.0.0. - Network accessline 43
`npx unbrowse mcp` (a stdio MCP for hosts that need one) uses the CLI sign-in; `unbrowse mcp add` registers it with Claude Code and Codex, so they run on that one sign-in. The other way: with no CLI sign-in, the CLI can use Claude Code's ow - Network accessline 45
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Network accessline 47
CLI and SDK: https://github.com/unbrowse-ai/unbrowse - Network accessline 51
Packaged installs that bundle this skill, connect Unbrowse and redirect the host's own browser to it (https://github.com/unbrowse-ai/unbrowse/tree/main/plugins): - Network accessline 96
- `GET https://unbrowse.ai/api/v1/sites/<host>/openapi.json`: OpenAPI 3.1, one operation per tool, typed inputs, an `example` input it was verified with, every status and header. No key needed to read. - Network accessline 97
[Credential-related source omitted] - Network accessline 100
Contract and examples: https://unbrowse.ai/docs/site-apis.md - Network accessline 143
Guide: https://unbrowse.ai/docs/orgs.md
plugins/claude-code/skills/unbrowse/references/tools.json
- Network accessline 1
{ "endpoint": "https://unbrowse.ai/mcp", - Network accessline 2
"endpoint": "https://unbrowse.ai/mcp", - Access to secretsline 188
[Credential-related source omitted] - Network accessline 350
"origin": { "type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 351
"type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." }, - Network accessline 352
"description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 376
"origin": { "type": "string", "description": "The site, e.g. https://github.com" - Network accessline 377
"type": "string", "description": "The site, e.g. https://github.com" }, - Network accessline 378
"description": "The site, e.g. https://github.com" - Access to secretsline 465
[Credential-related source omitted] - Network accessline 469
"url": { "type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 470
"type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" }, - Network accessline 471
"description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 530
"url": { "type": "string", "description": "Any page on the site, e.g. https://docs.rs" - Network accessline 531
"type": "string", "description": "Any page on the site, e.g. https://docs.rs" }, - Network accessline 532
"description": "Any page on the site, e.g. https://docs.rs" - Network accessline 555
"site": { "type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 556
"type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" } - Network accessline 557
"description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 686
"url": { "type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" - Network accessline 687
"type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" }, - Network accessline 688
"description": "The site or start page, e.g. https://www.ikea.com/sg/en/"
plugins/codex/skills/unbrowse/SKILL.md
- Network accessline 8
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below. - Network accessline 22
claude mcp add --transport http unbrowse https://unbrowse.ai/mcp - Network accessline 26
{"mcpServers":{"unbrowse":{"url":"https://unbrowse.ai/mcp"}}} - Network accessline 37
`unbrowse login` opens the sign-in page in the browser on this machine. The person enters their email, opens the link, presses **Allow**; the CLI prints `Signed in to https://unbrowse.ai (workspace ws_…)` and stores the token at `~/.config/ - Network accessline 39
From an agent's shell (no terminal for the person): run `npx unbrowse login --no-open` in the background, give the person the `https://unbrowse.ai/authorize?…` link it prints, and wait for the `Signed in` line. The link returns to `127.0.0. - Network accessline 43
`npx unbrowse mcp` (a stdio MCP for hosts that need one) uses the CLI sign-in; `unbrowse mcp add` registers it with Claude Code and Codex, so they run on that one sign-in. The other way: with no CLI sign-in, the CLI can use Claude Code's ow - Network accessline 45
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Network accessline 47
CLI and SDK: https://github.com/unbrowse-ai/unbrowse - Network accessline 51
Packaged installs that bundle this skill, connect Unbrowse and redirect the host's own browser to it (https://github.com/unbrowse-ai/unbrowse/tree/main/plugins): - Network accessline 96
- `GET https://unbrowse.ai/api/v1/sites/<host>/openapi.json`: OpenAPI 3.1, one operation per tool, typed inputs, an `example` input it was verified with, every status and header. No key needed to read. - Network accessline 97
[Credential-related source omitted] - Network accessline 100
Contract and examples: https://unbrowse.ai/docs/site-apis.md - Network accessline 143
Guide: https://unbrowse.ai/docs/orgs.md
plugins/codex/skills/unbrowse/references/tools.json
- Network accessline 1
{ "endpoint": "https://unbrowse.ai/mcp", - Network accessline 2
"endpoint": "https://unbrowse.ai/mcp", - Access to secretsline 188
[Credential-related source omitted] - Network accessline 350
"origin": { "type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 351
"type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." }, - Network accessline 352
"description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 376
"origin": { "type": "string", "description": "The site, e.g. https://github.com" - Network accessline 377
"type": "string", "description": "The site, e.g. https://github.com" }, - Network accessline 378
"description": "The site, e.g. https://github.com" - Access to secretsline 465
[Credential-related source omitted] - Network accessline 469
"url": { "type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 470
"type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" }, - Network accessline 471
"description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 530
"url": { "type": "string", "description": "Any page on the site, e.g. https://docs.rs" - Network accessline 531
"type": "string", "description": "Any page on the site, e.g. https://docs.rs" }, - Network accessline 532
"description": "Any page on the site, e.g. https://docs.rs" - Network accessline 555
"site": { "type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 556
"type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" } - Network accessline 557
"description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 686
"url": { "type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" - Network accessline 687
"type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" }, - Network accessline 688
"description": "The site or start page, e.g. https://www.ikea.com/sg/en/"
plugins/cursor/skills/unbrowse/SKILL.md
- Network accessline 8
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below. - Network accessline 22
claude mcp add --transport http unbrowse https://unbrowse.ai/mcp - Network accessline 26
{"mcpServers":{"unbrowse":{"url":"https://unbrowse.ai/mcp"}}} - Network accessline 37
`unbrowse login` opens the sign-in page in the browser on this machine. The person enters their email, opens the link, presses **Allow**; the CLI prints `Signed in to https://unbrowse.ai (workspace ws_…)` and stores the token at `~/.config/ - Network accessline 39
From an agent's shell (no terminal for the person): run `npx unbrowse login --no-open` in the background, give the person the `https://unbrowse.ai/authorize?…` link it prints, and wait for the `Signed in` line. The link returns to `127.0.0. - Network accessline 43
`npx unbrowse mcp` (a stdio MCP for hosts that need one) uses the CLI sign-in; `unbrowse mcp add` registers it with Claude Code and Codex, so they run on that one sign-in. The other way: with no CLI sign-in, the CLI can use Claude Code's ow - Network accessline 45
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Network accessline 47
CLI and SDK: https://github.com/unbrowse-ai/unbrowse - Network accessline 51
Packaged installs that bundle this skill, connect Unbrowse and redirect the host's own browser to it (https://github.com/unbrowse-ai/unbrowse/tree/main/plugins): - Network accessline 96
- `GET https://unbrowse.ai/api/v1/sites/<host>/openapi.json`: OpenAPI 3.1, one operation per tool, typed inputs, an `example` input it was verified with, every status and header. No key needed to read. - Network accessline 97
[Credential-related source omitted] - Network accessline 100
Contract and examples: https://unbrowse.ai/docs/site-apis.md - Network accessline 143
Guide: https://unbrowse.ai/docs/orgs.md
plugins/cursor/skills/unbrowse/references/tools.json
- Network accessline 1
{ "endpoint": "https://unbrowse.ai/mcp", - Network accessline 2
"endpoint": "https://unbrowse.ai/mcp", - Access to secretsline 188
[Credential-related source omitted] - Network accessline 350
"origin": { "type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 351
"type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." }, - Network accessline 352
"description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 376
"origin": { "type": "string", "description": "The site, e.g. https://github.com" - Network accessline 377
"type": "string", "description": "The site, e.g. https://github.com" }, - Network accessline 378
"description": "The site, e.g. https://github.com" - Access to secretsline 465
[Credential-related source omitted] - Network accessline 469
"url": { "type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 470
"type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" }, - Network accessline 471
"description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 530
"url": { "type": "string", "description": "Any page on the site, e.g. https://docs.rs" - Network accessline 531
"type": "string", "description": "Any page on the site, e.g. https://docs.rs" }, - Network accessline 532
"description": "Any page on the site, e.g. https://docs.rs" - Network accessline 555
"site": { "type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 556
"type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" } - Network accessline 557
"description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 686
"url": { "type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" - Network accessline 687
"type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" }, - Network accessline 688
"description": "The site or start page, e.g. https://www.ikea.com/sg/en/"
plugins/elizaos/skill/SKILL.md
- Network accessline 8
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below. - Network accessline 22
claude mcp add --transport http unbrowse https://unbrowse.ai/mcp - Network accessline 26
{"mcpServers":{"unbrowse":{"url":"https://unbrowse.ai/mcp"}}} - Network accessline 37
`unbrowse login` opens the sign-in page in the browser on this machine. The person enters their email, opens the link, presses **Allow**; the CLI prints `Signed in to https://unbrowse.ai (workspace ws_…)` and stores the token at `~/.config/ - Network accessline 39
From an agent's shell (no terminal for the person): run `npx unbrowse login --no-open` in the background, give the person the `https://unbrowse.ai/authorize?…` link it prints, and wait for the `Signed in` line. The link returns to `127.0.0. - Network accessline 43
`npx unbrowse mcp` (a stdio MCP for hosts that need one) uses the CLI sign-in; `unbrowse mcp add` registers it with Claude Code and Codex, so they run on that one sign-in. The other way: with no CLI sign-in, the CLI can use Claude Code's ow - Network accessline 45
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Network accessline 47
CLI and SDK: https://github.com/unbrowse-ai/unbrowse - Network accessline 51
Packaged installs that bundle this skill, connect Unbrowse and redirect the host's own browser to it (https://github.com/unbrowse-ai/unbrowse/tree/main/plugins): - Network accessline 96
- `GET https://unbrowse.ai/api/v1/sites/<host>/openapi.json`: OpenAPI 3.1, one operation per tool, typed inputs, an `example` input it was verified with, every status and header. No key needed to read. - Network accessline 97
[Credential-related source omitted] - Network accessline 100
Contract and examples: https://unbrowse.ai/docs/site-apis.md - Network accessline 143
Guide: https://unbrowse.ai/docs/orgs.md
plugins/elizaos/skill/references/tools.json
- Network accessline 1
{ "endpoint": "https://unbrowse.ai/mcp", - Network accessline 2
"endpoint": "https://unbrowse.ai/mcp", - Access to secretsline 188
[Credential-related source omitted] - Network accessline 350
"origin": { "type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 351
"type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." }, - Network accessline 352
"description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 376
"origin": { "type": "string", "description": "The site, e.g. https://github.com" - Network accessline 377
"type": "string", "description": "The site, e.g. https://github.com" }, - Network accessline 378
"description": "The site, e.g. https://github.com" - Access to secretsline 465
[Credential-related source omitted] - Network accessline 469
"url": { "type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 470
"type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" }, - Network accessline 471
"description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 530
"url": { "type": "string", "description": "Any page on the site, e.g. https://docs.rs" - Network accessline 531
"type": "string", "description": "Any page on the site, e.g. https://docs.rs" }, - Network accessline 532
"description": "Any page on the site, e.g. https://docs.rs" - Network accessline 555
"site": { "type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 556
"type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" } - Network accessline 557
"description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 686
"url": { "type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" - Network accessline 687
"type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" }, - Network accessline 688
"description": "The site or start page, e.g. https://www.ikea.com/sg/en/"
plugins/grok-build/skills/unbrowse/SKILL.md
- Network accessline 8
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below. - Network accessline 22
claude mcp add --transport http unbrowse https://unbrowse.ai/mcp - Network accessline 26
{"mcpServers":{"unbrowse":{"url":"https://unbrowse.ai/mcp"}}} - Network accessline 37
`unbrowse login` opens the sign-in page in the browser on this machine. The person enters their email, opens the link, presses **Allow**; the CLI prints `Signed in to https://unbrowse.ai (workspace ws_…)` and stores the token at `~/.config/ - Network accessline 39
From an agent's shell (no terminal for the person): run `npx unbrowse login --no-open` in the background, give the person the `https://unbrowse.ai/authorize?…` link it prints, and wait for the `Signed in` line. The link returns to `127.0.0. - Network accessline 43
`npx unbrowse mcp` (a stdio MCP for hosts that need one) uses the CLI sign-in; `unbrowse mcp add` registers it with Claude Code and Codex, so they run on that one sign-in. The other way: with no CLI sign-in, the CLI can use Claude Code's ow - Network accessline 45
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Network accessline 47
CLI and SDK: https://github.com/unbrowse-ai/unbrowse - Network accessline 51
Packaged installs that bundle this skill, connect Unbrowse and redirect the host's own browser to it (https://github.com/unbrowse-ai/unbrowse/tree/main/plugins): - Network accessline 96
- `GET https://unbrowse.ai/api/v1/sites/<host>/openapi.json`: OpenAPI 3.1, one operation per tool, typed inputs, an `example` input it was verified with, every status and header. No key needed to read. - Network accessline 97
[Credential-related source omitted] - Network accessline 100
Contract and examples: https://unbrowse.ai/docs/site-apis.md - Network accessline 143
Guide: https://unbrowse.ai/docs/orgs.md
plugins/grok-build/skills/unbrowse/references/tools.json
- Network accessline 1
{ "endpoint": "https://unbrowse.ai/mcp", - Network accessline 2
"endpoint": "https://unbrowse.ai/mcp", - Access to secretsline 188
[Credential-related source omitted] - Network accessline 350
"origin": { "type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 351
"type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." }, - Network accessline 352
"description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 376
"origin": { "type": "string", "description": "The site, e.g. https://github.com" - Network accessline 377
"type": "string", "description": "The site, e.g. https://github.com" }, - Network accessline 378
"description": "The site, e.g. https://github.com" - Access to secretsline 465
[Credential-related source omitted] - Network accessline 469
"url": { "type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 470
"type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" }, - Network accessline 471
"description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 530
"url": { "type": "string", "description": "Any page on the site, e.g. https://docs.rs" - Network accessline 531
"type": "string", "description": "Any page on the site, e.g. https://docs.rs" }, - Network accessline 532
"description": "Any page on the site, e.g. https://docs.rs" - Network accessline 555
"site": { "type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 556
"type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" } - Network accessline 557
"description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 686
"url": { "type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" - Network accessline 687
"type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" }, - Network accessline 688
"description": "The site or start page, e.g. https://www.ikea.com/sg/en/"
plugins/hermes/skills/unbrowse/SKILL.md
- Network accessline 8
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below. - Network accessline 22
claude mcp add --transport http unbrowse https://unbrowse.ai/mcp - Network accessline 26
{"mcpServers":{"unbrowse":{"url":"https://unbrowse.ai/mcp"}}} - Network accessline 37
`unbrowse login` opens the sign-in page in the browser on this machine. The person enters their email, opens the link, presses **Allow**; the CLI prints `Signed in to https://unbrowse.ai (workspace ws_…)` and stores the token at `~/.config/ - Network accessline 39
From an agent's shell (no terminal for the person): run `npx unbrowse login --no-open` in the background, give the person the `https://unbrowse.ai/authorize?…` link it prints, and wait for the `Signed in` line. The link returns to `127.0.0. - Network accessline 43
`npx unbrowse mcp` (a stdio MCP for hosts that need one) uses the CLI sign-in; `unbrowse mcp add` registers it with Claude Code and Codex, so they run on that one sign-in. The other way: with no CLI sign-in, the CLI can use Claude Code's ow - Network accessline 45
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Network accessline 47
CLI and SDK: https://github.com/unbrowse-ai/unbrowse - Network accessline 51
Packaged installs that bundle this skill, connect Unbrowse and redirect the host's own browser to it (https://github.com/unbrowse-ai/unbrowse/tree/main/plugins): - Network accessline 96
- `GET https://unbrowse.ai/api/v1/sites/<host>/openapi.json`: OpenAPI 3.1, one operation per tool, typed inputs, an `example` input it was verified with, every status and header. No key needed to read. - Network accessline 97
[Credential-related source omitted] - Network accessline 100
Contract and examples: https://unbrowse.ai/docs/site-apis.md - Network accessline 143
Guide: https://unbrowse.ai/docs/orgs.md
plugins/hermes/skills/unbrowse/references/tools.json
- Network accessline 1
{ "endpoint": "https://unbrowse.ai/mcp", - Network accessline 2
"endpoint": "https://unbrowse.ai/mcp", - Access to secretsline 188
[Credential-related source omitted] - Network accessline 350
"origin": { "type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 351
"type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." }, - Network accessline 352
"description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 376
"origin": { "type": "string", "description": "The site, e.g. https://github.com" - Network accessline 377
"type": "string", "description": "The site, e.g. https://github.com" }, - Network accessline 378
"description": "The site, e.g. https://github.com" - Access to secretsline 465
[Credential-related source omitted] - Network accessline 469
"url": { "type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 470
"type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" }, - Network accessline 471
"description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 530
"url": { "type": "string", "description": "Any page on the site, e.g. https://docs.rs" - Network accessline 531
"type": "string", "description": "Any page on the site, e.g. https://docs.rs" }, - Network accessline 532
"description": "Any page on the site, e.g. https://docs.rs" - Network accessline 555
"site": { "type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 556
"type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" } - Network accessline 557
"description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 686
"url": { "type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" - Network accessline 687
"type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" }, - Network accessline 688
"description": "The site or start page, e.g. https://www.ikea.com/sg/en/"
plugins/openclaw/skills/unbrowse/SKILL.md
- Network accessline 8
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below. - Network accessline 22
claude mcp add --transport http unbrowse https://unbrowse.ai/mcp - Network accessline 26
{"mcpServers":{"unbrowse":{"url":"https://unbrowse.ai/mcp"}}} - Network accessline 37
`unbrowse login` opens the sign-in page in the browser on this machine. The person enters their email, opens the link, presses **Allow**; the CLI prints `Signed in to https://unbrowse.ai (workspace ws_…)` and stores the token at `~/.config/ - Network accessline 39
From an agent's shell (no terminal for the person): run `npx unbrowse login --no-open` in the background, give the person the `https://unbrowse.ai/authorize?…` link it prints, and wait for the `Signed in` line. The link returns to `127.0.0. - Network accessline 43
`npx unbrowse mcp` (a stdio MCP for hosts that need one) uses the CLI sign-in; `unbrowse mcp add` registers it with Claude Code and Codex, so they run on that one sign-in. The other way: with no CLI sign-in, the CLI can use Claude Code's ow - Network accessline 45
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Network accessline 47
CLI and SDK: https://github.com/unbrowse-ai/unbrowse - Network accessline 51
Packaged installs that bundle this skill, connect Unbrowse and redirect the host's own browser to it (https://github.com/unbrowse-ai/unbrowse/tree/main/plugins): - Network accessline 96
- `GET https://unbrowse.ai/api/v1/sites/<host>/openapi.json`: OpenAPI 3.1, one operation per tool, typed inputs, an `example` input it was verified with, every status and header. No key needed to read. - Network accessline 97
[Credential-related source omitted] - Network accessline 100
Contract and examples: https://unbrowse.ai/docs/site-apis.md - Network accessline 143
Guide: https://unbrowse.ai/docs/orgs.md
plugins/openclaw/skills/unbrowse/references/tools.json
- Network accessline 1
{ "endpoint": "https://unbrowse.ai/mcp", - Network accessline 2
"endpoint": "https://unbrowse.ai/mcp", - Access to secretsline 188
[Credential-related source omitted] - Network accessline 350
"origin": { "type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 351
"type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." }, - Network accessline 352
"description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 376
"origin": { "type": "string", "description": "The site, e.g. https://github.com" - Network accessline 377
"type": "string", "description": "The site, e.g. https://github.com" }, - Network accessline 378
"description": "The site, e.g. https://github.com" - Access to secretsline 465
[Credential-related source omitted] - Network accessline 469
"url": { "type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 470
"type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" }, - Network accessline 471
"description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 530
"url": { "type": "string", "description": "Any page on the site, e.g. https://docs.rs" - Network accessline 531
"type": "string", "description": "Any page on the site, e.g. https://docs.rs" }, - Network accessline 532
"description": "Any page on the site, e.g. https://docs.rs" - Network accessline 555
"site": { "type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 556
"type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" } - Network accessline 557
"description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 686
"url": { "type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" - Network accessline 687
"type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" }, - Network accessline 688
"description": "The site or start page, e.g. https://www.ikea.com/sg/en/"
skill/SKILL.md
- Network accessline 8
Use the hosted service at `https://unbrowse.ai`. Execution, indexed routes and website sessions stay server-side. This skill supplies operating guidance; signing in is OAuth, below. - Network accessline 22
claude mcp add --transport http unbrowse https://unbrowse.ai/mcp - Network accessline 26
{"mcpServers":{"unbrowse":{"url":"https://unbrowse.ai/mcp"}}} - Network accessline 37
`unbrowse login` opens the sign-in page in the browser on this machine. The person enters their email, opens the link, presses **Allow**; the CLI prints `Signed in to https://unbrowse.ai (workspace ws_…)` and stores the token at `~/.config/ - Network accessline 39
From an agent's shell (no terminal for the person): run `npx unbrowse login --no-open` in the background, give the person the `https://unbrowse.ai/authorize?…` link it prints, and wait for the `Signed in` line. The link returns to `127.0.0. - Network accessline 43
`npx unbrowse mcp` (a stdio MCP for hosts that need one) uses the CLI sign-in; `unbrowse mcp add` registers it with Claude Code and Codex, so they run on that one sign-in. The other way: with no CLI sign-in, the CLI can use Claude Code's ow - Network accessline 45
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Network accessline 47
CLI and SDK: https://github.com/unbrowse-ai/unbrowse - Network accessline 51
Packaged installs that bundle this skill, connect Unbrowse and redirect the host's own browser to it (https://github.com/unbrowse-ai/unbrowse/tree/main/plugins): - Network accessline 96
- `GET https://unbrowse.ai/api/v1/sites/<host>/openapi.json`: OpenAPI 3.1, one operation per tool, typed inputs, an `example` input it was verified with, every status and header. No key needed to read. - Network accessline 97
[Credential-related source omitted] - Network accessline 100
Contract and examples: https://unbrowse.ai/docs/site-apis.md - Network accessline 143
Guide: https://unbrowse.ai/docs/orgs.md
skill/references/tools.json
- Network accessline 1
{ "endpoint": "https://unbrowse.ai/mcp", - Network accessline 2
"endpoint": "https://unbrowse.ai/mcp", - Access to secretsline 188
[Credential-related source omitted] - Network accessline 350
"origin": { "type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 351
"type": "string", "description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." }, - Network accessline 352
"description": "Only logins usable on this site, e.g. https://github.com. Pass it whenever you know the site." - Network accessline 376
"origin": { "type": "string", "description": "The site, e.g. https://github.com" - Network accessline 377
"type": "string", "description": "The site, e.g. https://github.com" }, - Network accessline 378
"description": "The site, e.g. https://github.com" - Access to secretsline 465
[Credential-related source omitted] - Network accessline 469
"url": { "type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 470
"type": "string", "description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" }, - Network accessline 471
"description": "A page, document or JSON API URL, e.g. https://docs.rs/serde or https://api.example.com/v1/items?q=x" - Network accessline 530
"url": { "type": "string", "description": "Any page on the site, e.g. https://docs.rs" - Network accessline 531
"type": "string", "description": "Any page on the site, e.g. https://docs.rs" }, - Network accessline 532
"description": "Any page on the site, e.g. https://docs.rs" - Network accessline 555
"site": { "type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 556
"type": "string", "description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" } - Network accessline 557
"description": "A site or URL, e.g. instagram.com or https://www.instagram.com/direct/inbox/" - Network accessline 686
"url": { "type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" - Network accessline 687
"type": "string", "description": "The site or start page, e.g. https://www.ikea.com/sg/en/" }, - Network accessline 688
"description": "The site or start page, e.g. https://www.ikea.com/sg/en/"
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 24 facts
- Network access in code of the SKILL.mdunbrowse/SKILL.md:22High confidence
- Network access in prose of the SKILL.mdunbrowse/SKILL.md:39Low confidence
- Network access in prose of the SKILL.mdunbrowse/SKILL.md:43Low confidence
- Network access in code of the SKILL.mdunbrowse/SKILL.md:22High confidence
- Network access in prose of the SKILL.mdunbrowse/SKILL.md:39Low confidence
- Network access in prose of the SKILL.mdunbrowse/SKILL.md:43Low confidence
- Network access in code of the SKILL.mdunbrowse/SKILL.md:22High confidence
- Network access in prose of the SKILL.mdunbrowse/SKILL.md:39Low confidence
- Network access in prose of the SKILL.mdunbrowse/SKILL.md:43Low confidence
- Network access in code of the SKILL.mdskill/SKILL.md:22High confidence
- Network access in prose of the SKILL.mdskill/SKILL.md:39Low confidence
- Network access in prose of the SKILL.mdskill/SKILL.md:43Low confidence
- Network access in code of the SKILL.mdunbrowse/SKILL.md:22High confidence
- Network access in prose of the SKILL.mdunbrowse/SKILL.md:39Low confidence
- Network access in prose of the SKILL.mdunbrowse/SKILL.md:43Low confidence
- Network access in code of the SKILL.mdunbrowse/SKILL.md:22High confidence
- Network access in prose of the SKILL.mdunbrowse/SKILL.md:39Low confidence
- Network access in prose of the SKILL.mdunbrowse/SKILL.md:43Low confidence
- Network access in code of the SKILL.mdunbrowse/SKILL.md:22High confidence
- Network access in prose of the SKILL.mdunbrowse/SKILL.md:39Low confidence
- Network access in prose of the SKILL.mdunbrowse/SKILL.md:43Low confidence
- Network access in code of the SKILL.mdskill/SKILL.md:22High confidence
- Network access in prose of the SKILL.mdskill/SKILL.md:39Low confidence
- Network access in prose of the SKILL.mdskill/SKILL.md:43Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugins/claude-code/skills/unbrowse/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Native | Manifest gemini-extension.json | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugins/claude-code/skills/unbrowse/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/claude-code/skills/unbrowse/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/unbrowse-ai-unbrowse/)