Skip to main content
Glama
openlinkedinmcp

openlinkedinmcp

openlinkedinmcp

Playwright-powered MCP server for LinkedIn. Automate jobs, profile edits, messaging, network actions, feed posts, and more using a real logged-in browser session.

LinkedIn’s official API cannot cover most member actions. This server drives linkedin.com in Chromium instead. UI changes can break selectors — treat tools as best-effort automation.

Requirements

  • Node.js 20+

  • Chromium for Playwright (npx playwright install chromium)

Related MCP server: LinkedIn MCP Server

Setup

npm install
npm run build

Register this server in your MCP client config (builds if needed, merges without wiping other servers):

./scripts/install.sh            # interactive: Cursor, Claude, or both
./scripts/install.sh --cursor   # ~/.cursor/mcp.json
./scripts/install.sh --claude   # Claude Code (~/.claude.json) and Desktop if present
./scripts/install.sh --both
./scripts/install.sh --dry-run --both   # preview only

Or via npm:

npm run install:mcp -- --cursor

Claude targets: Claude Code CLI (claude mcp add when available, else ~/.claude.json) and Claude Desktop (claude_desktop_config.json on macOS/Linux/Windows when the app config dir exists).

Session data (cookies / browser profile) is stored at:

~/.openlinkedinmcp/browser-profile

Override with OPENLINKEDINMCP_DATA_DIR.

Manual MCP config

If you prefer to edit configs by hand, add (path must be absolute):

{
  "mcpServers": {
    "openlinkedinmcp": {
      "command": "node",
      "args": ["/absolute/path/to/openlinkedinmcp/dist/index.js"],
      "env": {
        "OPENLINKEDINMCP_HEADLESS": "1"
      }
    }
  }
}

Typical locations:

  • Cursor: ~/.cursor/mcp.json

  • Claude Code: ~/.claude.json

  • Claude Desktop (macOS): ~/Library/Application Support/Claude/claude_desktop_config.json

  • Claude Desktop (Linux): ~/.config/Claude/claude_desktop_config.json

For local iteration without building:

{
  "command": "npx",
  "args": ["tsx", "/absolute/path/to/openlinkedinmcp/src/index.ts"]
}

First-time login

  1. Call linkedin_login from your MCP client.

  2. A visible browser window opens on LinkedIn’s login page.

  3. Sign in (complete 2FA if prompted).

  4. When the feed loads, the tool returns success and the session is reused.

Environment flags:

Variable

Meaning

OPENLINKEDINMCP_HEADLESS=0

Always show the browser

OPENLINKEDINMCP_LOGIN_TIMEOUT_MS

Login wait (default 300000)

OPENLINKEDINMCP_TIMEOUT_MS

Default Playwright timeout

OPENLINKEDINMCP_DATA_DIR

Custom data directory

Tools

Auth

  • linkedin_login — interactive Playwright login

  • linkedin_auth_status

  • linkedin_logout

Profile

  • get_my_profile, get_profile

  • update_headline, update_about

  • open_profile_section — experience, education, skills, featured, interests, contact-info

Jobs

  • search_jobs, get_job, save_job

  • get_saved_jobs, get_job_applications

  • easy_apply_job — defaults to dry_run=true

Feed

  • get_feed, create_post, like_post, comment_on_post, repost

Messaging

  • list_conversations, get_conversation, send_message, start_conversation

Network

  • search_people, send_connection_request

  • get_pending_invitations, accept_invitation

  • get_connections, follow_person

Companies & notifications

  • search_companies, get_company, follow_company

  • get_notifications

Browser helpers

  • navigate, screenshot_page, close_browser

Destructive or outbound actions (create_post, send_message, easy_apply_job, connection requests, etc.) support dry_run where noted. Prefer dry runs until you trust the flow.

Scripts

npm run dev          # stdio MCP via tsx
npm run build        # compile to dist/
npm run typecheck    # tsc --noEmit
npm start            # node dist/index.js
npm run install:mcp  # register with Cursor / Claude (see Setup)

License

MIT (see LICENSE).

Available Tools

36 tools
accept_invitationC

Accept the Nth pending invitation (1-based) on the invitation manager page.

Inputs: nth.

close_browserA

Close the Playwright browser context (session cookies remain on disk).

Inputs: no named parameters.

comment_on_postC

Comment on a LinkedIn post URL.

Inputs: comment (required), post_url (required), dry_run.

create_postB

Create a LinkedIn text post on your feed.

Inputs: text (required), dry_run.

easy_apply_jobA

Start LinkedIn Easy Apply on a job. By default only opens the form (dry_run=true). Set dry_run=false to submit the first step if possible.

Inputs: job (required), note, dry_run.

follow_companyC

Follow a LinkedIn company page.

Inputs: company (required).

follow_personB

Follow a person from their profile page.

Inputs: profile (required).

get_companyC

Open a LinkedIn company page by slug or URL and return visible text.

Inputs: company (required).

get_connectionsC

Open your connections list and return visible people links.

Inputs: limit, keywords.

get_conversationB

Open a messaging thread by 1-based index from list_conversations, or by thread URL.

Inputs: index, thread_url.

get_feedB

Open the LinkedIn home feed and return visible post text.

Inputs: max_chars.

get_jobB

Open a LinkedIn job posting and return its visible details.

Inputs: job (required).

get_job_applicationsC

Open My Jobs / applications view and return visible text.

Inputs: no named parameters.

get_my_profileA

Open your LinkedIn profile and return visible profile text.

Inputs: no named parameters.

get_notificationsC

Open LinkedIn notifications and return visible items.

Inputs: max_chars.

get_pending_invitationsB

List pending invitation / connection requests.

Inputs: no named parameters.

get_profileA

Open a LinkedIn profile by vanity name or full profile URL and return visible text.

Inputs: profile (required).

get_saved_jobsB

List jobs you have saved on LinkedIn.

Inputs: limit.

like_postA

Like a post currently visible on the feed, or open a post URL and like it.

Inputs: nth, post_url.

linkedin_auth_statusB

Check whether the saved Playwright session is logged into LinkedIn.

Inputs: no named parameters.

linkedin_loginB

Open a visible browser for LinkedIn sign-in. Complete email/password (and 2FA if prompted). Session is saved for later tools.

Inputs: timeout_ms.

linkedin_logoutB

Sign out of LinkedIn in the automation browser and close the browser context.

Inputs: no named parameters.

list_conversationsC

Open LinkedIn messaging and list visible conversation threads.

Inputs: limit.

open_profile_sectionC

Open a profile edit section (experience, education, skills, etc.) and return visible text for further guided edits.

Inputs: section (required).

repostB

Repost (reshare) a LinkedIn post URL, optionally with a thought.

Inputs: post_url (required), dry_run, thought.

save_jobB

Save / bookmark a LinkedIn job posting.

Inputs: job (required).

screenshot_pageC

Capture a PNG screenshot of the current page (base64).

Inputs: url, full_page.

search_companiesC

Search LinkedIn companies by keywords.

Inputs: keywords (required), limit.

search_jobsC

Search LinkedIn jobs by keywords and optional filters.

Inputs: keywords (required), limit, remote, location, +2 more.

search_peopleC

Search LinkedIn people by keywords.

Inputs: keywords (required), limit.

send_connection_requestB

Send a connection request to a LinkedIn profile, with optional note.

Inputs: profile (required), note, dry_run.

send_messageC

Send a message in the currently open thread, a thread URL, or by conversation index.

Inputs: message (required), index, dry_run, thread_url.

start_conversationC

Start a new LinkedIn message to a person by profile URL or vanity name.

Inputs: message (required), profile (required), dry_run.

update_aboutA

Update your LinkedIn About / summary section.

Inputs: about (required).

update_headlineC

Update your LinkedIn headline via the profile intro edit modal.

Inputs: headline (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 36 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes targeting different resources/actions (profiles, companies, jobs, messaging, feed). There is minor potential confusion between get_company vs search_companies, get_profile vs search_people, and follow_company vs follow_person, but the descriptions clarify the distinction between search vs direct access. The messaging tools (list_conversations, get_conversation, start_conversation, send_message) are well-separated by their distinct operations.

    Naming Consistency4/5

    The naming follows a strong verb_noun pattern throughout: get_*, search_*, create_*, follow_*, update_*, send_*, etc. A few slight deviations exist like linkedin_login, linkedin_auth_status, linkedin_logout (using the linkedin_ prefix rather than a verb_noun pattern) and navigate, screenshot_page, close_browser which don't follow the resource-targeting pattern, but the majority is highly consistent.

    Tool Count3/5

    36 tools is on the heavy end for a domain that could be consolidated. The server covers many sub-domains (profiles, companies, jobs, messaging, feed, notifications, auth), so the breadth justifies part of the count, but auth helpers (login, logout, auth_status) and utility tools (navigate, screenshot_page, close_browser) could arguably be grouped or reduced. Still, each tool serves a distinct function.

    Completeness5/5

    The tool surface is remarkably comprehensive for LinkedIn automation. It covers authentication lifecycle (login, auth_status, logout), profile viewing/editing (get_profile, get_my_profile, update_headline, update_about, open_profile_section), jobs lifecycle (search, get, save, easy_apply, saved, applications), messaging (list, get, start, send), feed engagement (get_feed, create_post, like, comment, repost), and networking (connections, people search, connection requests, invitations). There are no obvious dead-end operations.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      An MCP server for LinkedIn automation that enables users to search for jobs, retrieve profile details, manage connections, and read or send messages. It leverages Playwright and Browserbase to interact with LinkedIn through an existing authenticated browser session.
      6
      1
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Fully featured MCP server that provides automation tools for LinkedIn, supporting browser-based scraping and API-based operations for content management, media uploads, and reactions.
      6
      4
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      MCP server for programmable LinkedIn automation via Playwright, offering 20 tools for profile management, messaging, feed interaction, and job searching through real browser automation.
      -
    • A
      license
      A
      quality
      C
      maintenance
      A standalone MCP server that exposes typed LinkedIn capabilities (jobs, people, companies, posts, invitations, messaging) through the visible LinkedIn web UI, enabling workflow automation.
      31
      28 PyPI
      7
      Apache 2.0