- Home
- MCP servers
- python
6
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"filipptrigub-linkedin-mcp": {
"command": "linkedin-mcp",
"args": [],
"env": {
"LINKEDIN_CLIENT_ID": "<yours>",
"LINKEDIN_REDIRECT_URI": "<yours>",
"LINKEDIN_CLIENT_SECRET": "<yours>"
}
}
}
}You can post text updates and media to LinkedIn directly from Claude Desktop by using the LinkedIn MCP Server. It handles OAuth2 authentication, secure token storage, and flexible post options, so you can publish text, attach images or videos, and control who can see your updates.
How to use
To publish to LinkedIn through your MCP client, first authenticate to your LinkedIn MCP Server using the authenticate tool. Then create posts with the create_post tool, optionally attaching media by specifying the file path to the media you want to include. You can set the visibility of each post to public or connections only, and the server will handle OAuth2 token management for you.
Usage flow at a glance:
- Authenticate with LinkedIn using the authenticate tool.
- Create a post with create_post, providing your post text and optionally a media file path.
- The server stores tokens securely and uses them to post on your behalf according to the visibility you specify.
How to install
Prerequisites: you need Python installed on your machine and access to install Python tools.
# Install pipx if it is not already installed
pip install pipx
# Install the LinkedIn MCP server package
pipx install linkedin-mcp
Additional setup steps
Prepare environment variables for OAuth and the app configuration.
LINKEDIN_CLIENT_ID=your_client_id
LINKEDIN_CLIENT_SECRET=your_client_secret
LINKEDIN_REDIRECT_URI=http://localhost:3000/callback
Claude Desktop configuration
Add the LinkedIn MCP server to your Claude Desktop configuration, providing your OAuth credentials as environment variables.
{
"mcpServers": {
"linkedin-mcp": {
"command": "linkedin-mcp",
"env": {
"LINKEDIN_CLIENT_ID": "<yours>",
"LINKEDIN_CLIENT_SECRET": "<yours>",
"LINKEDIN_REDIRECT_URI": "<yours>"
}
}
}
}
Development and testing
For development and testing you can run the server locally using the development workflow shown below. Ensure your environment variables are set before starting the server.
{
"mcpServers": {
"linkedin-mcp": {
"command": "uv",
"args": [
"--directory",
"absolute\\path\\to\\linkedin-mcp",
"run",
"-m",
"linkedin_mcp.server"
],
"env": {
"LINKEDIN_CLIENT_ID": "<yours>",
"LINKEDIN_CLIENT_SECRET": "<yours>",
"LINKEDIN_REDIRECT_URI": "<yours>"
}
}
}
}
Notes on credentials and security
Treat all OAuth credentials as secrets. Do not expose your client secret or redirect URI in public places. The server stores tokens securely for reuse across sessions.
Available tools
authenticate
Authenticate with LinkedIn to obtain OAuth2 tokens and grant access to post on your behalf.
create_post
Create a LinkedIn post with text and optional media attachment by specifying a media file path.