Outx MCP Server
MCP server for OutX β LinkedIn social listening & data API
Ask AI about Outx MCP Server
Powered by Claude Β· Grounded in docs
I know everything about Outx MCP Server. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
OutX MCP Server
MCP server for the OutX LinkedIn social listening and data API. Connect AI agents like Claude, Cursor, and Claude Code to LinkedIn β create watchlists, search posts, fetch profiles, and engage, all through natural language.
AI Agent ββ MCP Protocol ββ OutX MCP Server ββ OutX API ββ LinkedIn
What You Can Do
- Monitor LinkedIn β Track posts by keywords, people, or companies with watchlists
- Search & filter posts β 15+ filters: keyword, date, seniority, trending, language
- Fetch profiles & companies β Get full LinkedIn profiles, company pages, and connections
- Search LinkedIn β Find people by title, company, location, industry, and more
- Message connections β Send direct messages to 1st-degree connections
- Engage β Like and comment on posts through your LinkedIn account
- All via natural language β Just tell your AI agent what you want
Quick Start
1. Get an API key at mentions.outx.ai/api-doc
2. Add to your AI tool (pick one):
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"outx": {
"command": "npx",
"args": ["-y", "outx-mcp-server"],
"env": {
"OUTX_API_KEY": "your-api-key"
}
}
}
}
Cursor
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"outx": {
"command": "npx",
"args": ["-y", "outx-mcp-server"],
"env": {
"OUTX_API_KEY": "your-api-key"
}
}
}
}
Claude Code
Add to .mcp.json in your project:
{
"mcpServers": {
"outx": {
"command": "npx",
"args": ["-y", "outx-mcp-server"],
"env": {
"OUTX_API_KEY": "your-api-key"
}
}
}
}
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"outx": {
"command": "npx",
"args": ["-y", "outx-mcp-server"],
"env": {
"OUTX_API_KEY": "your-api-key"
}
}
}
}
3. Start using it:
"Create a watchlist to monitor LinkedIn posts about AI startups raising Series A"
Available Tools (26)
Watchlist Management
Pause and resume any watchlist with disable: true or disable: false on its update tool. Configure Slack alerts with slack_webhook_url.
| Tool | Description |
|---|---|
create_keyword_watchlist | Create a watchlist that monitors LinkedIn posts matching keywords. Two modes: pass keywords to track exact terms, OR pass a plain-English prompt and OutX will generate keywords and intent labels for you. Mutually exclusive. |
list_keyword_watchlists | List all keyword watchlists on your account. |
update_keyword_watchlist | Patch any combination of name, fetchFreqInHours, disable (pause/resume), slack_webhook_url, keywords, or labels, OR pass prompt to have OutX wipe and regenerate keywords + labels from a new description. Patch and prompt modes are mutually exclusive. |
delete_keyword_watchlist | Delete a keyword watchlist and all tracked data. |
create_people_watchlist | Create a watchlist that tracks posts from specific LinkedIn profiles by URL or slug. |
list_people_watchlists | List all people watchlists on your account. |
update_people_watchlist | Patch a people watchlist: name, fetchFreqInHours, disable (pause/resume), or slack_webhook_url. |
delete_people_watchlist | Delete a people watchlist. |
create_company_watchlist | Create a watchlist that tracks posts from LinkedIn company pages by URL or slug. |
list_company_watchlists | List all company watchlists on your account. |
update_company_watchlist | Patch a company watchlist: name, fetchFreqInHours, disable (pause/resume), or slack_webhook_url. |
delete_company_watchlist | Delete a company watchlist. |
Posts & Engagement (operates on posts your watchlists captured)
| Tool | Description |
|---|---|
get_posts | Search and filter posts from your watchlists (keyword, date, seniority, trending, language, etc.) |
get_interactions | Retrieve likes and comments for posts in a watchlist with filtering, pagination, and daily graph data. |
like_watchlist_post | Like a post by its OutX post_id (from get_posts results). For liking by LinkedIn activity URN, use like_linkedin_post. |
comment_on_watchlist_post | Comment on a post by its OutX post_id (from get_posts results). For commenting by LinkedIn activity URN, use comment_on_linkedin_post. |
LinkedIn Data API (direct LinkedIn actions, no watchlist required)
Async tools, the MCP server polls LinkedIn for ~150s and returns the result directly. You almost never need get_task_status because of this.
| Tool | Description |
|---|---|
fetch_linkedin_profile | Fetch full LinkedIn profile by slug (name, headline, experience, education, skills). |
fetch_linkedin_profile_posts | Fetch recent posts from one or more profiles by URN. |
fetch_linkedin_company | Fetch company page data by slug (industry, employee count, description, headquarters). |
fetch_linkedin_company_posts | Fetch recent posts from a company page with engagement data. |
fetch_linkedin_connections | Fetch your 1st-degree connections with keyword search and pagination. |
search_linkedin_profiles | Search LinkedIn profiles by title, company, location, industry, and more. |
send_linkedin_message | Send a direct message to a 1st-degree connection by recipient URN. |
like_linkedin_post | Like a post by its LinkedIn activity URN. For liking a post that came from a watchlist, use like_watchlist_post. |
comment_on_linkedin_post | Comment on a post by its LinkedIn activity URN. For commenting on a post that came from a watchlist, use comment_on_watchlist_post. |
get_task_status | Recovery only. Use this when another tool returns a "did not complete within 150s" error, pass the api_agent_task_id from that error to check whether the task has since finished. Don't retry the original tool, that creates a duplicate and wastes a daily quota slot. |
Note: LinkedIn Data tools require the OutX Chrome extension to be active within the last 48 hours.
Example Prompts
Once connected, try these with your AI agent:
Social listening:
- "Create a watchlist to monitor LinkedIn posts about AI startups raising Series A"
- "Show me trending posts from my watchlists this week"
- "What are VPs and Directors posting about machine learning?"
- "Find posts mentioning our competitor from the last 7 days"
Profile & company research:
- "Fetch the LinkedIn profile for williamhgates"
- "Get recent posts from this prospect's profile"
- "Get company info and recent posts for OpenAI"
- "Search for VPs of Engineering at Google in the US"
- "Show me my most recently added connections"
Engagement & messaging:
- "Like the top 3 most engaging posts about product management"
- "Comment on this post with a thoughtful response"
- "Send a message to this connection thanking them for connecting"
Workflows:
- "Set up a watchlist for 'looking for a CRM' and check it every 6 hours"
- "List all my watchlists and show me posts from the sales signals one"
Prerequisites
- Node.js 18+ β Required for the MCP server runtime
- OutX account β Sign up free and get your API key
- OutX Chrome extension β Required for LinkedIn Data API tools (profile fetching, direct engagement). Install here
How It Works
The OutX API has two surfaces:
-
Watchlists & Engagement API (sync) β Create watchlists to monitor LinkedIn by keywords, people, or companies. OutX scans on your schedule and stores posts. Query and engage via API.
-
LinkedIn Data API (async) β Direct LinkedIn proxy. Fetch profiles, get posts, like, comment. All endpoints return a task ID; the MCP server polls automatically until the result is ready.
The MCP server wraps both APIs into 28 tools that any MCP-compatible AI agent can call.
Development
git clone https://github.com/outxai/outx-mcp-server.git
cd outx-mcp-server
npm install
npm run build
OUTX_API_KEY=your-key npm start
For development with auto-reload:
OUTX_API_KEY=your-key npm run dev
Documentation
- MCP Integration Guide β Detailed setup and configuration
- API Reference β Full REST API documentation
- API Quick Start β Create watchlists and retrieve posts
- LinkedIn Data API Quick Start β Fetch profiles in 2 minutes
- Authentication Guide β API keys and OTP auth
- Rate Limits β Usage limits and best practices
- API Use Cases β Sales signals, competitor monitoring, hiring alerts
- Chrome Extension β Required for LinkedIn Data tools
- LinkedIn Safety Guide β Rate limiting and account protection
Integrations
- Python SDK β Drop-in Python wrapper for the OutX API
- LangChain Integration β Use OutX as a LangChain tool for AI agents
- n8n Integration β No-code LinkedIn automation workflows
Guides & Tutorials
- How to Connect AI Agents to LinkedIn β LangChain, Claude, GPT, and MCP examples
- LinkedIn API Guide β Comprehensive API overview
- LinkedIn API Alternatives 2026 β OutX vs Proxycurl vs PhantomBuster vs Unipile
- How to Build a Sales Signal Pipeline β Detect buying intent with the OutX API
- LinkedIn Competitor Monitoring Guide β Track competitor activity via API
- Social Listening on LinkedIn β Complete guide to LinkedIn monitoring
- How to Automate LinkedIn Likes & Comments β Engagement automation best practices
- LinkedIn Automation Safety Guide β Keep your account safe
Links
- OutX Platform β Sign up and get started
- Get API Key β Generate your API key
- OutX for AI Agents β All AI integration options (MCP, skill file, llms.txt)
- Pricing β Free, Pro, and Enterprise plans
- FAQ β Common questions answered
Partnerships
Interested in a collaboration or affiliate partnership? Drop us a message at support@outx.ai.
License
MIT
