Linkedin MCP Server

Post to LinkedIn directly from Claude Desktop with support for text and media attachments.

Local serverstdio

What is the Linkedin MCP MCP server?

Linkedin mcp mcp server connects Linkedin MCP to AI assistants that speak the Model Context Protocol. Post to LinkedIn directly from Claude Desktop with support for text and media attachments.

What Linkedin MCP does

Post to LinkedIn directly from Claude Desktop with support for text and media attachments.

Key capabilities

  • Post text updates to LinkedIn
  • Attach images and videos to posts
  • Control post visibility (public/connections)
  • OAuth2 authentication flow
  • Secure token storage

Tools it exposes

Once connected, the assistant can call these 2 tools directly:

  • authenticate — Authenticate with LinkedIn
  • create_post — Create and share posts optionally with media attachments

Installing the linkedin mcp mcp server

The server is distributed via PyPI as pipx, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

Before the server will start you need to supply 3 environment variables: LINKEDIN_CLIENT_ID, LINKEDIN_CLIENT_SECRET, LINKEDIN_REDIRECT_URI. Keep credentials in your client's env block or a secrets manager rather than committing them.

Where it fits

File and storage servers are what separate an assistant that talks about your documents from one that actually works with them. Linkedin MCP sits in that group, and the shape of its toolset — authenticate, create_post — tells you what it is really for. Worth comparing against the other file systems servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • Maintained by FilippTrigub.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the linkedin mcp mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
authenticateAuthenticate with LinkedIn
create_postCreate and share posts optionally with media attachments

How to install the Linkedin MCP MCP server

{
  "mcpServers": {
    "linkedin": {
      "command": "uvx",
      "args": ["pipx"],
      "env": {
        "LINKEDIN_CLIENT_ID": "your-value",
        "LINKEDIN_CLIENT_SECRET": "your-value",
        "LINKEDIN_REDIRECT_URI": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
LINKEDIN_CLIENT_IDConfiguration value read at startup.Optional
LINKEDIN_CLIENT_SECRETCredential the server authenticates with.Yes
LINKEDIN_REDIRECT_URIFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Linkedin MCP to authenticate.
  • Use Linkedin MCP to create post.

Frequently asked questions

It connects Linkedin MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (authenticate, create_post) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Linkedin MCP directly.