Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@LinkedIn MCP Server Share a post on LinkedIn about our new feature release"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server using the TypeScript SDK for LinkedIn integration. Allows an AI agent (e.g. Claude) to authenticate with LinkedIn and share posts or links.
Node.js (>=14) and npm
LinkedIn Developer App:
Create an app at https://www.linkedin.com/developers/apps
Under "Products", add Sign In with LinkedIn (OpenID Connect) and Share on LinkedIn
Authorized Redirect URI must match .env: http://localhost:8000/auth/linkedin/callback
Copy your Client ID and Client Secret into .env
Related MCP server: LinkedIn MCP Server
git clone <repo_url>
cd linkedin-mcp
npm installCreate a .env in project root with:
SESSION_SECRET=your-session-secret
AUTH_PORT=8000 # OAuth callback server port
HTTP_PORT=8001 # HTTP/SSE server port
LINKEDIN_CLIENT_ID=your-client-id
LINKEDIN_CLIENT_SECRET=your-client-secret
LINKEDIN_REDIRECT_URI=http://localhost:8000/auth/linkedin/callbackOAuth Callback Server (must stay running):
npm run dev:authMCP Server:
Via Claude Desktop:
claude-desktopOr manually:
npm run devThis starts stdio transport + HTTP+SSE server.
Inspector UI:
npm run build
npx @modelcontextprotocol/inspector node build/server.jsOpen the Inspector in browser → Tools
Use linkedin-share-post or linkedin-share-link tools.
Visit http://localhost:8000/auth/linkedin in browser → complete LinkedIn login.
Confirm “Authentication successful!”.
In Inspector, run sample post/link tools.
Verify content on your LinkedIn profile.
Run npm run dev:auth
Visit http://localhost:8000/auth/linkedin in browser → complete LinkedIn login.
Confirm “Authentication successful!”. A token file should be generated. Do not close this terminal.
Open Claude Desktop and verify the tools are listed
Configure your claude_desktop_config.json file:
{
"mcpServers": {
"linkedin": {
"command": "node",
"args": ["/Users/ken/Desktop/lab/linkedin-mcp/build/server.js"],
"transport": "http",
"url": "http://localhost:8001",
"sseEndpoint": "/stream",
"httpEndpoint": "/message",
"env": {
"SESSION_SECRET": "your-session-secret",
"AUTH_PORT": "8000",
"HTTP_PORT": "8001",
"LINKEDIN_CLIENT_ID": "your-client-id",
"LINKEDIN_CLIENT_SECRET": "your-client-secret",
"LINKEDIN_REDIRECT_URI": "http://localhost:8000/auth/linkedin/callback"
}
}
},
"globalShortcut": "Ctrl+Space"
}(You can find this file from Claude Desktop by going to settings > developer > edit config)
Save and restart Claude Desktop to apply changes.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0linkedin-share-linklinkedin-share-postScored across 2 tools
The two tools are clearly distinct: one shares a link with commentary, the other shares a text post. No overlap in purpose.
Both tools follow the consistent pattern 'linkedin-share-{type}', using snake_case and a clear verb_noun structure.
Two tools is somewhat thin for a LinkedIn server; while it covers two core posting actions, it feels like a minimal offering for the social network domain.
The server covers link sharing and text posting, but misses image/video posts, schedule, and profile operations, leaving notable gaps for typical LinkedIn usage.
LinkedIn for AI agents: inbox, invitations, Sales Navigator search, posts. Quotas and webhooks.
Give AI agents the LinkedIn tools to find, qualify, engage, and follow up with prospects.
Let AI tools securely access your LinkedIn network and DMs
Full LinkedIn access for AI agents: leads, messaging, and campaigns with safe limits built in.
