Featured

Deploy OpenClaw in 60 seconds β€” 20% off logoDeploy OpenClaw in 60 seconds β€” 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger β†’
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger β†’
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free β†’
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free β†’
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data β€” no proxies, no parsers, no maintenance.

Start building free β†’
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it β€” secured from day one.

Get it set up for you β†’
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free β†’
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here β†’

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

devag7/linkedin-mcp MCP server](https://glama.ai/mcp/servers/devag7/linkedin-mcp/badges/score.svg)](https://glama.ai/mcp/servers/devag7/linkedin-mcp) πŸ“‡ 🏠 - LinkedIn for AI assistants over an authenticated browser session β€” profiles, people/job/company...

README.md

<div align="center">

πŸ”— LinkedIn MCP

LinkedIn for AI assistants β€” structured data via a real, stealth browser session

![CI](https://github.com/devag7/linkedin-mcp/actions/workflows/ci.yml) ![npm version](https://www.npmjs.com/package/linkedin-mcp-tools) ![MIT License](LICENSE) ![TypeScript](https://www.typescriptlang.org/) ![MCP](https://modelcontextprotocol.io/) ![Glama score](https://glama.ai/mcp/servers/devag7/linkedin-mcp)

Give Claude, Cursor, and any MCP client access to LinkedIn β€” profiles, people/job/company search, feed, messaging, and your network β€” as clean structured JSON.

22 tools Β· reads + gated writes (connect, message, post, react, comment) Β· a real safety layer (daily caps, human pacing, circuit breaker) Β· 166 tests.

⚠️ Automating LinkedIn violates its User Agreement and can get an account restricted. No tool is ban-proof β€” and this one says so up front. Use a secondary account; read Account safety and DISCLAIMER.md first.

</div>

---

Why this exists

LinkedIn's internal Voyager API (the one its own web app uses) returns rich, structured JSON β€” but it sits behind Cloudflare bot-management, which rejects plain HTTP requests (a stateless fetch or curl gets stuck in an endless redirect, even with a valid cookie). The only reliable way to read LinkedIn data programmatically in 2026 is from inside a real browser that clears the challenge.

This project's approach:

  1. Drive a real Chrome via patchright (an undetected Playwright fork) so Cloudflare's challenge is solved with a genuine browser fingerprint.
  2. Query Voyager from inside the authenticated page β€” same-origin, the exact network path LinkedIn's own SPA uses β†’ structured JSON, not scraped DOM text.

That last point is the edge over DOM-scraping tools: in-page API calls are locale-independent and resilient to UI redesigns, so they don't break on a moved CSS selector or a translated label.

---

✨ What's good here

| | | |---|---| | 🧩 Structured JSON | In-page Voyager API calls return normalized data, shaped into compact objects β€” not brittle innerText scraping. | | ✍️ Writes are API calls, not button-clicking | connect / message / post / react / comment POST straight to Voyager β€” the exact requests the web app sends, captured and verified live. No hunting for a "Connect" button under a sticky navbar, no composer-dialog race. Every write returns a structured status (ok / duplicate / already_connected / restricted / quota_exhausted / …) β€” never a blind "sent: true". | | πŸ›‘οΈ Safety layer built in | Serial queue, human-paced jittered delays, per-action daily budgets, account warmup ramp, and a circuit breaker that hard-stops on any checkpoint/captcha. (Risk reduction β€” not a safety guarantee.) | | πŸ”₯ One warm session | A single persistent browser per process (cookies + Cloudflare clearance survive restarts). Explicit close_session, signal-handled teardown β€” no zombie Chrome. | | 🌍 Locale-independent | API + embedded-JSON parsing, not English-only DOM selectors β€” survives UI redesigns and translations. | | πŸ”’ Local & private | Session stored under ~/.linkedin-mcp/ with 0700/0600 perms; no cookies/tokens to paste, none ever logged. |

---

How it compares

| | DOM-scraping LinkedIn MCPs | This | |---|---|---| | Reads | scraped page text (brittle, locale-bound) | structured API JSON | | Writes (connect/message/post) | click rendered buttons (break on sticky navbars, dialog races, localized labels) | direct Voyager POST, captured + verified live | | Write feedback | "clicked it" β†’ hope | structured status (ok / duplicate / restricted / quota_exhausted / …) | | Resilience | breaks on UI tweaks / translations | API + embedded-JSON, locale-proof | | Safety (caps, pacing, circuit breaker) | none | βœ… built-in, 166 tests | | Zombie browser processes | common | βœ… reaped on close | | Language | Python | TypeScript + official MCP SDK |

We hit LinkedIn's own API from inside the challenge-passed browser β€” reads and writes β€” so you get the structured response and a real status, not parsed HTML and a hopeful click.

πŸ“¦ Status

Stable β€” v2, all 22 tools shipping. Full transparency on exactly where every piece stands:

| Area | State | |---|---| | Stealth browser engine (patchright) | βœ… built, live-proven | | In-page Voyager fetch (the core mechanism) | βœ… live-verified (returns structured JSON) | | Safety layer (queue / pacer / budgets / circuit-breaker) | βœ… built, 166 unit tests | | Profile β€” get_profile, get_my_profile (name, headline, summary, experience, education, skills, certifications, languages) | βœ… live-verified | | Feed / notifications β€” get_feed, get_notifications | βœ… live-verified | | Jobs / messaging β€” search_jobs, get_job_details, get_inbox, get_conversation | βœ… live-verified | | People / companies β€” search_people, search_companies, get_company, get_company_posts, get_company_employees (DOM fallback) | βœ… live-verified | | Network β€” get_pending_invitations (received + sent) | βœ… | | Session β€” whoami, health_check (live Voyager probe + budget headroom), close_session | βœ… | | Write tools β€” connect_with_person, send_message, create_post, react_to_post, comment_on_post | βœ… all 5 endpoints captured + live-verified on a burner; gated (confirm:true + daily caps), structured statuses. ⚠️ These take real, often irreversible actions β€” keep the gate on and use a throwaway account. |

22 tools. typecheck + 166 tests green.

Login is headful, the server is headless. The one-time --login opens a real Chrome window (to clear Cloudflare and let you solve any captcha/2FA). After that the persistent profile carries the clearance, so the server runs headless β€” verified returning live data. Use a residential IP; datacenter/VPN IPs are often pre-flagged by Cloudflare regardless of headless vs headful.

---

πŸš€ Quick start

1. Log in once (opens a real Chrome window β€” sign in, solve any captcha/2FA):

npx -y linkedin-mcp-tools@latest --login

Needs Google Chrome installed (or run npx patchright install chrome once). Your session β€” Cloudflare clearance and all β€” persists to ~/.linkedin-mcp/profile/.

2. Point your MCP client at it. Claude Desktop / Cursor / Claude Code config:

{
  "mcpServers": {
    "linkedin": {
      "command": "npx",
      "args": ["-y", "linkedin-mcp-tools@latest"]
    }
  }
}

Then just ask: "Get my LinkedIn profile and summarize my experience" or "Find 5 recruiters at Google."

<details> <summary><b>From source / contributing</b></summary>

git clone https://github.com/devag7/linkedin-mcp.git
cd linkedin-mcp
npm install
npm run setup:browser     # installs the Chrome patchright drives
npm run login             # log in once
npm run spike             # verify: fetches your profile as JSON
npm run build             # produces dist/

MCP config: "command": "node", "args": ["/absolute/path/to/dist/index.js"]. </details>

Headless / server deployment

The one-time --login needs a window; the server then runs headless (verified returning live data). Run --login on a machine with a display (or via VNC), copy ~/.linkedin-mcp/profile/ to your server, and run there:

LINKEDIN_HEADLESS=true npx -y linkedin-mcp-tools@latest   # no display needed

Use a residential IP β€” datacenter/VPN IPs are frequently pre-flagged by Cloudflare regardless of headless vs headful.

---

πŸ›‘οΈ Account safety

Read this. Automating LinkedIn violates its User Agreement and can get your account restricted or banned β€” no tool can prevent that, including this one. The built-in safety features (daily caps, human pacing, warmup, circuit breaker) reduce risk; they do not eliminate it.

Defaults err conservative:

  • Connections 20/day, messages 50/day, likes+comments 50/day combined, follows 30/day β€” combined write cap 150/24h.
  • Profile views 80/day, searches 30/day.
  • New-account warmup ramp over the first weeks; pending-invite ceiling and acceptance-rate pauses.
  • Reads paced 4–12s apart, writes 45–150s, with long breaks and a working-hours gate.
  • A circuit breaker stops automatically on any checkpoint, captcha, or "unusual activity" page β€” and never tries to solve one.

Recommendations: use a secondary/throwaway account, run from a residential IP, warm it up slowly. See DISCLAIMER.md for the full legal/ToS notice.

---

βš™οΈ Configuration

| Variable | Default | Description | |---|---|---| | LINKEDIN_HEADLESS | true | Server runs headless. --login always opens a real window regardless. Set false to watch the browser. | | LINKEDIN_CHROME_PATH | β€” | Explicit Chrome binary path (else patchright's). | | LINKEDIN_PROFILE_DIR | ~/.linkedin-mcp/profile | Persistent browser profile. | | LINKEDIN_IDLE_TIMEOUT_MS | 300000 | Close the browser after this idle time (0 disables). | | LINKEDIN_CONCURRENCY | 1 | Serial by default; >1 is ban-risky. | | TRANSPORT | stdio | stdio (primary) or http. |

---

πŸ›  Development

npm run dev          # run from source (stdio)
npm run typecheck
npm test             # vitest (safety layer + smoke)
npm run build

---

πŸ“„ License

MIT β€” see LICENSE. Not affiliated with LinkedIn. Use at your own risk; see DISCLAIMER.md.

<div align="center">

![linkedin-mcp MCP server](https://glama.ai/mcp/servers/devag7/linkedin-mcp)

Made by Dev Agarwalla

</div>

See related servers & alternatives β†’

Related MCP servers

Browse all β†’

Related guides

Hand-picked reading to help you choose and use Search servers.