Skip to main content
Glama
Sign In
@isteam/linkedin-mcp

@isteam/linkedin-mcp

by isteamhq
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

@isteam/linkedin-mcp

npm version License: MIT

MCP server for LinkedIn — post, comment, react, and manage content via AI agents.

Built by is.team — the AI-native project management platform.

Quick Start

Add to your MCP config (.mcp.json for Claude Code, or Claude Desktop settings):

{
  "mcpServers": {
    "linkedin": {
      "command": "npx",
      "args": ["-y", "@isteam/linkedin-mcp"],
      "env": {
        "LINKEDIN_ACCESS_TOKEN": "your-access-token",
        "LINKEDIN_PERSON_ID": "your-person-id"
      }
    }
  }
}

Related MCP server: LinkedIn MCP Server

Tools (10)

Content & Engagement

Tool

Description

create_post

Create a LinkedIn text post (max 3000 characters)

create_article_post

Share an article link with commentary

delete_post

Delete a post by URN

comment_on_post

Comment on a post (max 1250 characters)

like_post

Like/react to a post

Profile & Analytics

Tool

Description

get_me

Get authenticated user info

get_post

Get a post by URN (text, author, stats)

get_comments

Get comments on a post

get_own_posts

Get your recent LinkedIn posts

get_post_stats

Get like/comment counts for a post

Environment Variables

Variable

Required

Description

LINKEDIN_ACCESS_TOKEN

Yes

OAuth 2.0 access token

LINKEDIN_PERSON_ID

Yes*

Your LinkedIn person ID (required in member mode)

LINKEDIN_ORGANIZATION_ID

No

Organization ID (for posting as a company page)

LINKEDIN_MODE

No

member (default) or organization

*Required when LINKEDIN_MODE is member (default).

Getting your credentials

  1. Create an app in the LinkedIn Developer Portal

  2. Request the w_member_social and r_liteprofile OAuth scopes

  3. Complete the OAuth 2.0 flow to get an access token

  4. Get your person ID from the /v2/userinfo endpoint

Organization mode

To post as a company page, set LINKEDIN_MODE=organization and provide LINKEDIN_ORGANIZATION_ID:

{
  "env": {
    "LINKEDIN_ACCESS_TOKEN": "your-access-token",
    "LINKEDIN_PERSON_ID": "your-person-id",
    "LINKEDIN_ORGANIZATION_ID": "your-org-id",
    "LINKEDIN_MODE": "organization"
  }
}

Rate Limits & Agent Safety

LinkedIn API enforces per-endpoint rate limits:

Endpoint

Limit

Notes

POST /rest/posts (create post)

1 req/sec, ~100/day

Stricter daily cap on content creation

POST /rest/socialActions/.../comments

2 req/sec

POST /rest/reactions (like)

1 req/sec

GET endpoints (posts, comments, stats)

~100 req/hour

Per authenticated user

General throttle

~60 req/min

Varies by endpoint scope

Idempotency note: LinkedIn does not deduplicate identical posts. If your agent retries on timeout, it may create duplicate content. Use get_own_posts to verify before retrying a create operation.

Backoff: When rate-limited, the API returns 429 with a Retry-After header (seconds). Wait the specified duration before retrying.

Usage Examples

Share a thought leadership post:

"Post on LinkedIn: AI agents are changing how teams collaborate. At is.team, we're building a future where AI joins your standups and ships features alongside you."

Share an article:

"Share this article on LinkedIn with a summary: https://example.com/article-about-ai"

Engage with your network:

"Get my recent LinkedIn posts and show their engagement stats"

About is.team

is.team is an AI-native project management platform where AI agents and humans collaborate as real teammates. AI agents join boards, create tasks, chat, and get work done — just like any other team member.

Part of the is.team open-source MCP ecosystem:

License

MIT

Available Tools

10 tools
comment_on_postA

Comment on a LinkedIn post (max 1250 chars). Requires post URN — use WebSearch to find posts, then get_post to get the URN.

Inputs: post_urn (required), text (required).

create_article_postC

Share an article link on LinkedIn with commentary

Inputs: text (required), article_url (required), article_title, article_description.

create_postA

Create a LinkedIn text post (max 3000 chars)

Inputs: text (required).

delete_postB

Delete a LinkedIn post by URN

Inputs: post_urn (required).

get_commentsC

Get comments on a LinkedIn post

Inputs: post_urn (required), count.

get_meA

Get authenticated LinkedIn user info

Inputs: no named parameters.

get_own_postsB

Get your own recent LinkedIn posts

Inputs: count.

get_postA

Get a LinkedIn post by URN (text, author, stats)

Inputs: post_urn (required).

get_post_statsB

Get like/comment counts for a LinkedIn post

Inputs: post_urn (required).

like_postA

Like/react to a LinkedIn post

Inputs: post_urn (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.6/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool targets a distinct action (e.g., create vs delete vs get stats) with clear boundaries. No two tools overlap in purpose.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (e.g., create_post, delete_post, get_comments) with underscores, making them predictable.

    Tool Count5/5

    10 tools cover the essential LinkedIn post lifecycle (CRUD plus comments, likes, stats) without being excessive or insufficient.

    Completeness4/5

    Missing an update/edit post tool, and repost/share functionality is absent. However, core operations are well-covered, and the gap is minor.

    Resources

    Related MCP Connectors

    Related MCP Servers