Skip to main content
Glama
Sign In
deenesjakoruzh
LinkedIn MCP Assistant

LinkedIn MCP Assistant

by ertiqah
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

LiGo + LinkedIn MCP Runner

How it works

The first GPT-powered creative co-pilot trained on your actual LinkedIn content.

Create posts. Analyze what’s working. Rewrite in your voice. All from Claude or ChatGPT, powered by your own past posts.

What is this?

This is the official runner repo for LiGo’s Model Context Protocol (MCP) - a protocol that lets GPT-based assistants pull your LinkedIn context and respond like a strategist. It works with both Claude and ChatGPT.

With MCP, your assistant can answer things like:

  • Which of your last posts got the most traction

  • What your writing tone actually sounds like

  • How to help you post, rewrite, or brainstorm like a founder

Just talk to it normally (if you know how to do that - no judging if you don't, btw). It has access to all your PUBLIC Linkedin data (with your consent, of course).

Related MCP server: linkedctl

How to Get Started

Claude Setup

  1. Download the Claude desktop app.

  2. Visit ligo.ertiqah.com/integrations/claude

  3. Click "Generate Installation Command"

    • If not logged in, you’ll be routed to authenticate with LiGo

  4. Copy the command and run it in your terminal

  5. Open Claude and start chatting

Example prompt:

Analyze my last 5 posts. What’s working? Give me ideas on what I should write next.

ChatGPT (CustomGPT)

No installation needed.

  1. Go to ligo.ertiqah.com/integrations/chatgpt

  2. Authenticate with LiGo when prompted

  3. Start using the CustomGPT

Example prompt:

Rewrite this to sound more like my recent posts and make the hook spicier.

See It in Action: MCP Leaderboard

We showcase the latest 50 posts made using the MCP integration, complete with:

  • The full post

  • A link to the original LinkedIn post

  • The author’s name

This acts like a public feed. It’s a live demo. And yes, it creates some healthy FOMO + you get a permanent backlink to your post. SEO goes brrrr.

Why It Matters

Honestly, it's a bit of a pain keeping your GPT/Claude Project up to date with your Linkedin activity (assuming you even have one).

We thought: "Wouldn't it be nice if GPT could connect to our Linkedin profile so I could just tell it to go look at it?"

And then this happened.

But, that's not all.

It’s part of the broader LigoSocial platform, which covers commenting, analytics, CRM, and more. Go check it out.

Also Check Out

Stay Updated

This README will be the canonical source for MCP runner updates.

For feedback, improvements, or integration ideas, open an issue or reach out via ligo.ertiqah.com/contact.

Available Tools

10 tools
analyze_linkedin_chatA

Ask questions about the user's LinkedIn profile, content, or network, with support for multi-turn conversations.

Inputs: query (required), conversation_history.

generate_linkedin_postA

Generate three LinkedIn post variants from any content (article, newsletter, notes, etc.) to optimize engagement.

Inputs: content (required), content_type.

get_linkedin_postsB

Retrieve the user's recent LinkedIn posts with engagement metrics.

Inputs: limit.

get_linkedin_profileA

Retrieve the user's LinkedIn profile information including headline, summary, experience, and education.

Inputs: no named parameters.

publish_linkedin_postB

Publish a text post to LinkedIn, optionally including media (images/videos) specified by URL.

Inputs: post_text (required), media.

publish_twitter_postC

Publish a text post (tweet) to Twitter.

Inputs: post_text (required).

refresh_linkedin_postsA

Force a refresh of LinkedIn posts data to capture recently published content.

Inputs: no named parameters.

refresh_linkedin_profileA

Force a refresh of the LinkedIn profile data to update any recent changes.

Inputs: no named parameters.

schedule_linkedin_postA

Schedule a text post for LinkedIn at a specific future date and time, optionally including media (images/videos) specified by URL.

Inputs: post_text (required), scheduled_date (required), media.

set_linkedin_urlA

Set or update the LinkedIn profile URL to analyze. Required before using profile/posts retrieval tools if not set previously.

Inputs: linkedin_url (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

    A3.8/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: profile retrieval, post retrieval, post generation, publishing, scheduling, refreshing, URL setting, and chat analysis. There is no overlap or ambiguity between them.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case (e.g., generate_linkedin_post, refresh_linkedin_profile). The naming is predictable and uniform, with the only minor outlier being publish_twitter_post, which still adheres to the same pattern.

    Tool Count5/5

    With 10 tools, the set is well-scoped for a LinkedIn assistant. It covers essential operations without being overwhelming or too sparse. Each tool earns its place.

    Completeness5/5

    The tool set covers the core LinkedIn workflows: profile retrieval, post listing, generation, publishing, scheduling, refreshing, and interactive chat. The inclusion of a Twitter publishing tool is a slight extension but does not create a gap in LinkedIn functionality.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • LinkedIn MCP

      devag7
      A
      license
      A
      quality
      B
      maintenance
      Released 3.0.0: 22 MCP tools, guided offline setup, local stdio, Chrome and manual login. No hosted deployment or job-research brief. Writes need opt-in, reviewed preview and human approval. Unofficial; provider compatibility, first-use cohorts, coordinated erasure and Windows privacy proof remain unverified. No mandatory paid service.
      22
      393 npm
      12
      MIT

    Appeared in Searches