linkedin-mcp-server
Open-source MCP server for LinkedIn enabling access to profiles, companies, jobs, and messages.
GraphCanon updated today · GitHub synced today
Decision brief
linkedin-mcp-server is an open-source MCP server for LinkedIn that supports integration with various AI agents like Claude, offering access to profiles, companies, jobs, and messages.
Good fit when
- To integrate MCP-compatible AI agents like Claude specifically with LinkedIn data for tasks such as job analysis or network augmentation
- When developing applications needing read-access to LinkedIn's profile, company, or job data in an MCP-compliant way
Avoid when
- If your project requires a proprietary solution that does not need open-source contributions
- For platforms or projects where support for the Model Context Protocol (MCP) is unnecessary or incompatible with existing workflows
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Adoption
Package downloads where a registry match exists. GitHub stars (3,222) are secondary evidence.
- Docker Hub pulls (30d)
- 46,538·Docker Hub API·today
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of today
- Provenance
- Not a fork · Personal account
- As of today
- Security (OSV)
- No lockfile
- As of 2w
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install linkedin-mcp-serverSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
This repository houses an open-source MCP server tailored for interaction with LinkedIn data including profiles, companies, and job listings. It supports integration with AI agents such as Claude that are compatible with the Model Context Protocol (MCP).
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Aug 26, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Aug 26, 2026
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Aug 26, 2026
- MCP server
- No MCP server detected
Source: repo_scan · Aug 26, 2026
- Languages
- python
Source: github.language+pyproject.toml · Aug 26, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 26, 2026)
- **Default (stdio)**: Standard communication for local MCP serversSource link
Tags
README
Installation Methods - MCP Server for LinkedIn
| Tool | Description |
|---|---|
get_person_profile | Get profile info with explicit section selection (experience, education, interests, honors, languages, certifications, skills, projects, contact_info, posts) |
get_my_profile | Get the authenticated user's own LinkedIn profile (same sections as get_person_profile) |
connect_with_person | Send a connection request or accept an incoming one, with optional note |
get_sidebar_profiles | Extract profile URLs from sidebar recommendation sections ("More profiles for you", "Explore premium profiles", "People you may know") on a profile page |
get_inbox | List recent conversations from the LinkedIn messaging inbox |
get_conversation | Read a specific messaging conversation by username or thread ID |
search_conversations | Search messages by keyword |
send_message | Send a message to a LinkedIn user (requires confirmation) |
get_company_profile | Extract company information with explicit section selection (posts, jobs); about-section references may include a company_urn entry carrying the numeric id used by LinkedIn's people-search currentCompany URL facet |
get_company_posts | Get recent posts from a company's LinkedIn feed |
search_companies | Search for companies on LinkedIn by keywords |
get_company_employees | List employees at a company from the /people/ page, with optional keyword filter |
search_jobs | Search for jobs with keywords and location filters |
get_saved_jobs | List job postings saved by the authenticated user |
search_people | Search for people by keywords, location, connection degree (1st/2nd/3rd), and current company |
get_job_details | Get detailed information about a specific job posting |
get_feed | Get recent posts from the authenticated user's home feed |
search_posts | Search posts/content globally by keyword (the "Posts" tab) with an optional recency filter (past-24h/past-week/past-month) |
close_session | Close browser session and clean up resources |
Installation
Client Configuration
{
"mcpServers": {
"mcp-server-linkedin": {
"command": "uvx",
"args": ["mcp-server-linkedin@latest"],
"env": { "UV_HTTP_TIMEOUT": "300" }
}
}
}
The @latest tag turns on automatic updates, which keep the server working with LinkedIn's current page structure. The server starts quickly, prepares the shared Patchright Chromium browser cache in the background under ~/.linkedin-mcp/patchright-browsers, and opens a LinkedIn login browser window on the first tool call that needs authentication.
AI agent? Get a quick confirmation from the user before enabling automatic updates.
[!NOTE] Early tool calls may return a setup/authentication-in-progress error until browser setup or login finishes. If you prefer to create a session explicitly, run
uvx mcp-server-linkedin@latest --login.
🐳 Docker Setup
Prerequisites: Make sure Docker is installed and running.
Docker Setup Help
🔧 Configuration
Transport Modes:
- Default (stdio): Standard communication for local MCP servers
- Streamable HTTP: For a web-based MCP server
- If no transport is specified, the server defaults to
stdio - An interactive terminal without explicit transport shows a chooser prompt
CLI Options:
--log-level {DEBUG,INFO,WARNING,ERROR}- Logging level (default: WARNING)--transport {stdio,streamable-http}- Force the transport mode (default: stdio)--host HOST/--port PORT/--path PATH- HTTP server address (defaults: 127.0.0.1, 8000, /mcp)--logout- Clear the stored session and every profile derived from it--timeout MS- Timeout for a single page operation (default: 5000)--tool-timeout SECONDS- Timeout for a whole tool call (default: 180). R
For agents
This page has a .md twin and JSON over the API.