Skip to main content
Glama
LinkedIn MCP Server

LinkedIn MCP Server

LinkedIn MCP Server

License: MIT Python 3.12+ LinkedIn API

Complete LinkedIn automation toolkit. Scrape profiles, manage posts, read any LinkedIn content, and automate interactions via MCP (Model Context Protocol).


๐Ÿ“˜ Table of Contents


Overview

linkedin-mcp is a fully featured MCP server that provides automation tools for LinkedIn.
It supports browser-based scraping and API-based operations for content management, media uploads, and reactions.

Repository: Linkedin MCP Server


Features

๐Ÿ” Scraping (Browser-Based)

  • Extract full LinkedIn profiles

  • Scrape company pages

  • Read job listings

  • Read ANY LinkedIn post

  • Extract images, videos, engagement metrics

๐Ÿ“ API-Based Post Management

  • Create, update, delete LinkedIn posts

  • Add or remove reactions

  • Upload images and documents

  • Supports all official LinkedIn REST API features

๐Ÿงฉ MCP Integration

  • Works with Claude Desktop and any MCP-compatible client

  • 17 total tools included

๐Ÿงช Testing

  • 50+ tests

  • Covers scraping, API, and MCP tools


Quickstart

Install

git clone https://github.com/selvin-paul-raj/Linkedin-MCP-Server.git
cd Linkedin-MCP-Server

# create environment config
cp .env.example .env

# install dependencies
pip install -e .

Run

# Standard MCP server
uv run linkedin-mcp

# Debug mode (shows browser)
uv run main.py --debug --no-headless --no-lazy-init

# HTTP mode
uv run main.py --transport streamable-http

Authentication

Related MCP server: LinkedIn MCP Pro Max

Get your li_at cookie:

  1. Log in to LinkedIn in Chrome

  2. Press F12

  3. Application โ†’ Cookies โ†’ https://www.linkedin.com

  4. Copy the li_at cookie value

  5. Add to .env:

LINKEDIN_COOKIE=li_at=YOUR_COOKIE_VALUE

2. API (OAuth Access Token)

Add these fields to .env:

LINKEDIN_CLIENT_ID=your_id
LINKEDIN_CLIENT_SECRET=your_secret
LINKEDIN_ACCESS_TOKEN=your_access_token
LINKEDIN_API_VERSION=202510
https://www.linkedin.com/oauth/v2/authorization?response_type=code&client_id=YOUR_CLIENT_ID&redirect_uri=YOUR_REDIRECT_URI&scope=w_member_social%20r_liteprofile%20r_emailaddress

Exchange auth code:

curl -X POST https://www.linkedin.com/oauth/v2/accessToken \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "grant_type=authorization_code" \
  -d "code=YOUR_CODE" \
  -d "redirect_uri=YOUR_REDIRECT_URI" \
  -d "client_id=YOUR_CLIENT_ID" \
  -d "client_secret=YOUR_CLIENT_SECRET"

Usage

Read any LinkedIn post

{
  "tool": "read_linkedin_post",
  "input": "https://www.linkedin.com/posts/...activity-123456..."
}

Create a post

{
  "tool": "create_linkedin_post",
  "input": {
    "text": "Excited to announce our new product launch! ๐Ÿš€",
    "visibility": "PUBLIC"
  }
}

Upload image

{
  "tool": "upload_linkedin_image",
  "input": { "image_url": "https://example.com/image.jpg" }
}

Claude Desktop Integration

Add this to claude_desktop_config.json:

{
  "mcpServers": {
    "linkedin": {
      "command": "uv",
      "args": [
        "--directory",
        "D:\\MCP\\linkedin-mcp",
        "run",
        "linkedin-mcp"
      ],
      "env": {
        "LINKEDIN_COOKIE": "li_at=YOUR_COOKIE",
        "LINKEDIN_ACCESS_TOKEN": "YOUR_TOKEN"
      }
    }
  }
}

Available Tools

๐Ÿ“– Content Reading

  • read_linkedin_post

๐ŸŒ Scraping

  • get_person_profile

  • get_company_profile

  • get_job_details

  • search_jobs

  • search_recommended_jobs

  • close_session

๐Ÿ“ Post Management

  • create_linkedin_post

  • update_linkedin_post

  • delete_linkedin_post

๐Ÿ–ผ๏ธ Media

  • upload_linkedin_image

  • get_linkedin_image

๐Ÿ’™ Reactions

  • add_linkedin_reaction

  • remove_linkedin_reaction

  • get_linkedin_reactions

๐Ÿ‘ค Profile & Auth

  • get_linkedin_profile

  • validate_linkedin_credentials

More details. See TOOLS_REFERENCE.md.


Project Structure

linkedin-mcp/
โ”œโ”€โ”€ linkedin_mcp_server/
โ”‚   โ”œโ”€โ”€ server.py
โ”‚   โ”œโ”€โ”€ cli.py
โ”‚   โ”œโ”€โ”€ config/
โ”‚   โ”œโ”€โ”€ drivers/
โ”‚   โ””โ”€โ”€ tools/
โ”œโ”€โ”€ tests/
โ”‚   โ”œโ”€โ”€ unit/
โ”‚   โ”œโ”€โ”€ integration/
โ”œโ”€โ”€ scripts/
โ”œโ”€โ”€ .env.example
โ”œโ”€โ”€ pyproject.toml
โ”œโ”€โ”€ README.md
โ””โ”€โ”€ TOOLS_REFERENCE.md

Testing

# unit tests
uv run pytest tests/unit -v

# integration tests
uv run pytest tests/integration -v

# all tests
uv run pytest tests/ -v

Quick API test:

uv run python scripts/test_api.py

Troubleshooting

โŒ "426 Client Error: Upgrade Required"

Fix:

LINKEDIN_API_VERSION=202510

Get fresh cookie from Chrome.

โŒ "401 Unauthorized"

Generate a new access token.

ChromeDriver issues

pip install --upgrade selenium webdriver-manager

API Versioning

Current default:

202510

Check latest: https://learn.microsoft.com/en-us/linkedin/marketing/versioning

Update:

LINKEDIN_API_VERSION=202511

Restart the server.


Contributing

git clone https://github.com/selvin-paul-raj/Linkedin-MCP-Server.git
cd Linkedin-MCP-Server
uv sync
uv run pytest tests/ -v
uv run ruff format .
uv run pre-commit run --all-files

Pull requests welcome.


License

MIT License. See the LICENSE file.


Disclaimer

This tool is for educational and automation purposes. Follow LinkedIn TOS, API terms, and usage limits. Use responsibly.


Built with โค๏ธ for LinkedIn automation

Available Tools

6 tools
close_sessionA

Close the current browser session and clean up resources.

Inputs: no named parameters. Returns: object

get_company_profileA

Get a specific company's LinkedIn profile.

Args: company_name (str): LinkedIn company name (e.g., "docker", "anthropic", "microsoft") get_employees (bool): Whether to scrape the company's employees (slower)

Returns: Dict[str, Any]: Structured data from the company's profile

Inputs: company_name (required), get_employees. Returns: object

get_job_detailsA

Get job details for a specific job posting on LinkedIn

Args: job_id (str): LinkedIn job ID (e.g., "4252026496", "3856789012")

Returns: Dict[str, Any]: Structured job data including title, company, location, posting date, application count, and job description (may be empty if content is protected)

Inputs: job_id (required). Returns: object

get_person_profileA

Get a specific person's LinkedIn profile.

Args: linkedin_username (str): LinkedIn username (e.g., "stickerdaniel", "anistji")

Returns: Dict[str, Any]: Structured data from the person's profile

Inputs: linkedin_username (required). Returns: object

search_jobsB

Search for jobs on LinkedIn using a search term.

Args: search_term (str): Search term to use for the job search.

Returns: List[Dict[str, Any]]: List of job search results

Inputs: search_term (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    TDQS

    A3.8/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool has a clear, distinct purpose: session management, company profiles, person profiles, job details, recommended jobs, and job search. No two tools overlap in functionality.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case (e.g., get_company_profile, search_jobs), making them predictable and easy to understand.

    Tool Count5/5

    With 6 tools, the set is well-scoped for a LinkedIn-focused server covering profiles and jobs without being overwhelming or sparse.

    Completeness3/5

    The tool surface covers basic read operations (profiles, jobs) but lacks common interaction capabilities like sending messages, posting updates, or managing connections, leaving notable gaps.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      A FastMCP-based server that enables programmatic LinkedIn automation and data extraction through browser automation, offering secure authentication and tools for profile operations and post interactions while respecting LinkedIn's rate limits.
      55
      -
    • A
      license
      A
      quality
      D
      maintenance
      High-performance autonomous MCP server that turns LinkedIn into an API for AI workflows, enabling profile management, job search, content posting, and document generation.
      14
      1
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      MCP server for programmable LinkedIn automation via Playwright, offering 20 tools for profile management, messaging, feed interaction, and job searching through real browser automation.
      -
    • F
      license
      A
      quality
      D
      maintenance
      MCP server for automating LinkedIn actions such as reading feeds, sending messages, creating posts, and managing connections. Uses browser automation with proxy and stealth support.
      21
      -