LinkedIn MCP Server
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 Create a LinkedIn post about my latest project"
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.
LinkedIn MCP Server
A Model Context Protocol (MCP) server for LinkedIn integration, allowing Claude to create posts, comment on posts, manage your LinkedIn presence, and share content with media attachments.
Features
Post Management: Create, delete, and view LinkedIn posts
Media Sharing: Upload and share images/videos with posts
Comment System: Comment on LinkedIn posts
Feed Management: View your LinkedIn feed
Profile Access: Get your LinkedIn profile information
Post Engagement: Like and share LinkedIn posts
Related MCP server: LinkedIn MCP Server
Prerequisites
Node.js 18+
LinkedIn Developer Account and Access Token
Claude Desktop App
Installation
Clone this repository:
git clone https://github.com/rgthelen/linkedin-mcp-server.git
cd linkedin-mcp-serverInstall dependencies:
npm installSet up LinkedIn API credentials:
Create an app or use existing app
Generate an access token with appropriate scopes:
r_liteprofile(to read profile)r_emailaddress(to read email)w_member_social(to post content)
Configure environment variables:
cp .env.example .env
# Edit .env with your LinkedIn access tokenBuild the project:
npm run buildConfiguration
See CLAUDE.md for detailed Claude Desktop setup instructions.
Available Tools
test_linkedin_connection- Test the LinkedIn API connectionget_profile- Get your LinkedIn profile informationcreate_post- Create a new LinkedIn post (with optional media)delete_post- Delete a LinkedIn postget_post- Get details of a specific postget_feed- Get posts from your LinkedIn feedcomment_post- Comment on a LinkedIn postlike_post- Like a LinkedIn postshare_post- Share a LinkedIn post
Usage Examples
With Claude Desktop configured, you can ask Claude:
"Create a LinkedIn post about my latest project"
"Share this image with a caption about AI developments"
"Comment on this LinkedIn post with my professional thoughts"
"Show me my recent LinkedIn feed"
"Get my LinkedIn profile information"
Media Support
The server supports uploading images and videos according to LinkedIn's official API v2 specification:
Supported formats: JPG, PNG, GIF (images), MP4, MOV, AVI (videos)
Process: Automatic media upload, registration, and post creation
Usage: Just provide the file path when creating posts
License
MIT
Available Tools
9 toolscreate_commentC
Comment on a LinkedIn post
Inputs: postUrn (required), text (required).
create_postB
Create a new LinkedIn post with optional media
Inputs: text (required), visibility, articleUrl, mediaPath, +1 more.
delete_postB
Delete a LinkedIn post
Inputs: postId (required).
get_feedB
Get posts from your LinkedIn feed
Inputs: count.
get_postB
Get details of a specific LinkedIn post
Inputs: postId (required).
get_profileA
Get your LinkedIn profile information
Inputs: no named parameters.
like_postB
Like a LinkedIn post
Inputs: postUrn (required).
test_linkedin_connectionA
Test the LinkedIn MCP Server connection
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Each tool has a distinct purpose: commenting, posting, deleting, viewing feed/post/profile, liking, sharing, and testing. No overlapping functionality.
All tool names follow a consistent verb_noun pattern with underscores (e.g., create_post, get_feed, like_post). The naming convention is uniform.
9 tools is well-scoped for a LinkedIn server, covering essential actions without being excessive or insufficient.
The set covers core LinkedIn interactions (posting, commenting, liking, sharing, viewing), but lacks tools for retrieving comments or updating posts, which are minor gaps.
Maintenance
Related MCP Connectors
LinkedIn MCP for Claude, ChatGPT, Grok, Hermes: triage inbox, comment, find people, live profiles
LinkedIn for AI agents: search people, read profiles, posts and connections via a connected account
LinkedIn actions for AI agents: search, messaging, posts and invites, as hosted MCP tools.
Publish and schedule LinkedIn posts from your AI assistant.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables posting text and media content directly to LinkedIn from Claude Desktop with support for authentication and visibility controls.12MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to interact with LinkedIn for posting, commenting, liking, and managing connections via OAuth2 authentication.MIT
- AlicenseAqualityDmaintenanceEnables Claude Desktop to manage your LinkedIn profile and company pages, including posting, reading posts, and fetching profile information.74MIT
- AlicenseAqualityDmaintenanceEnables posting content, sharing articles, and managing your LinkedIn profile through Claude using the official LinkedIn API with OAuth 2.0.69 npmMIT