linkedin-mcp
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 find me remote data scientist jobs posted this week"
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
An MCP server that lets an AI assistant search LinkedIn jobs and read LinkedIn profiles, by driving a real Chrome window over the DevTools protocol.
It is read-only. There is no tool here that connects, messages, endorses, posts or applies — not as a setting, but because the code to do it does not exist. That is a deliberate line: LinkedIn treats automated writing far more harshly than automated reading, and mixing the two is what gets accounts restricted.
Tools
Tool | What it returns |
| Listings with title, company, location, workplace type, salary when posted, posted age, and |
| One posting in full — company, location, LinkedIn's job insights, and the whole description with the "See more" clamp expanded. |
| Name, headline, location, about text, experience history, education and skills. |
| Whether the saved browser session is still signed in. |
| Detaches from Chrome, leaving the window and session alone. |
Related MCP server: LinkedIn Job Scraper MCP Server
Install
Requires Python 3.12+, uv, and Google Chrome.
git clone https://github.com/TSS99/linkedin-mcp.git
cd linkedin-mcp
uv syncSign in once. This opens a Chrome window and waits for you to log in by hand — credentials are never typed by the script, because LinkedIn challenges scripted credential entry:
uv run linkedin-mcp --loginThe session persists in ~/.linkedin-mcp/chrome-profile. Check it any time with
uv run linkedin-mcp --check, clear it with uv run linkedin-mcp --logout.
Which Chrome profile it drives
By default the server opens a throwaway profile of its own. That window will look brand new — no bookmarks, no extensions, signed into nothing but LinkedIn. That is the point: the server can only ever see LinkedIn.
If you would rather it drove your everyday Chrome, so it reuses the LinkedIn session you already have and does not open a stranger window, set:
LINKEDIN_MCP_PROFILE_DIR=systemor point it at any profile directory explicitly. In an MCP client config that
goes in the env block:
{
"mcpServers": {
"linkedin": {
"command": "uv",
"args": ["--directory", "/path/to/linkedin-mcp", "run", "linkedin-mcp"],
"env": { "LINKEDIN_MCP_PROFILE_DIR": "system" }
}
}
}Two things to understand before you do:
You still have to restart Chrome once. --remote-debugging-port only takes
effect at launch; it cannot be switched on for a process that is already
running. So a Chrome that is open right now can never be attached to, whatever
the profile setting says. Quit it fully (Cmd+Q, not just closing the window)
and let the server start it, or start it yourself with the command
--login prints.
The debug port is not LinkedIn-scoped. Anything that can reach
127.0.0.1:9224 can drive every tab in that Chrome and read every session
in it — your mail, your bank, all of it — not just LinkedIn. On the isolated
profile there is nothing else to reach. On your everyday profile there is
everything. Run it that way only on a machine you trust, and close the debug
Chrome when you are done.
--logout refuses to delete a profile it did not create, so pointing this at
your real Chrome cannot wipe your browser state.
Configure
Add to your MCP client config (see mcp-config.example.json):
{
"mcpServers": {
"linkedin": {
"command": "uv",
"args": ["--directory", "/path/to/linkedin-mcp", "run", "linkedin-mcp"]
}
}
}For Claude Code: claude mcp add linkedin -- uv --directory /path/to/linkedin-mcp run linkedin-mcp
How it works, and why
CDP against a real Chrome profile, not a launched browser. Playwright's own
Chromium advertises itself in a dozen ways LinkedIn checks. Attaching to a real
Chrome you logged into yourself keeps the fingerprint and the cookie honest.
The server runs on debug port 9224, so it coexists with other browser-driven
MCP servers on 9222/9223.
Navigations are paced. LinkedIn rate-limits on cadence, not just volume, so
goto enforces a jittered minimum gap. A long research run is slower than it
could be, on purpose.
Every string in LinkedIn's DOM appears twice — once visible, once in a
visually-hidden span for screen readers — so raw innerText reads as
"Acme Corp\nAcme Corp". dedupe_lines collapses consecutive repeats; without
it every parsed field comes out doubled.
Selectors are ordered fallback lists. LinkedIn's class names are obfuscated
and renamed often. Where possible the parsers anchor on things that have
outlived the class churn — the data-occludable-job-id attribute, the stable
div#experience anchor ids — and fall back to parsing line order out of card
text rather than trusting a per-field hook.
A broken scrape never returns an empty result. Every tool is wrapped so a
missing anchor comes back as {"status": "error", "error_type": "stale_selector", ...} naming the selector and URL. An LLM handed [] will
report "no jobs found" with total confidence; this makes tool breakage and
genuine emptiness distinguishable.
Tests
uv run pytestThe tests cover the pure parsers — URL/filter construction, card parsing, profile entry parsing, line deduplication — against fixtures in the shape LinkedIn's DOM actually produces. They need no browser and no network.
When it breaks
It will. LinkedIn ships markup changes constantly, and a scraper is a guess
about someone else's HTML. Expect stale_selector errors eventually; the fix
is usually one more entry in a selector list in tools/jobs.py or
tools/profiles.py, plus a fixture in tests/test_parsers.py.
If you get auth_required with a checkpoint URL, LinkedIn wants a human:
open the Chrome window, clear the challenge, and retry.
A word on terms of use
Automated access is against LinkedIn's User Agreement regardless of how careful the implementation is, and LinkedIn does restrict accounts for it. This is a personal research tool; read-only design and paced requests reduce the risk but do not eliminate it, and the account you point it at is the one that carries that risk. Use your judgement.
Licence
Apache-2.0
Available Tools
5 toolslinkedin_check_sessionA
Check whether the browser is signed in to LinkedIn.
Every other tool needs this to be true; LinkedIn serves a login wall to anonymous visitors on job listings and profiles alike.
Inputs: no named parameters.
linkedin_close_sessionA
Disconnect from the browser and free resources.
This detaches from Chrome; it leaves the window and the saved session alone.
Inputs: no named parameters.
linkedin_get_jobA
Get the full detail for one job posting.
Returns the title, company, location, posted age, LinkedIn's job insights (seniority, employment type, headcount) and the complete job description with the "See more" clamp expanded.
Inputs: job (required).
linkedin_get_profileA
Read a LinkedIn profile.
Returns name, headline and location, plus the about text, experience history, education and listed skills unless include_sections is false.
Set include_sections to false when you only need to confirm who someone is; it is one page load either way but a much smaller result.
Inputs: profile (required), include_sections.
linkedin_search_jobsA
Search job listings on LinkedIn.
Returns each listing with title, company, location, workplace type, posted salary where the employer provided one, how long ago it was posted, and the job_id. Pass that job_id to linkedin_get_job for the full description rather than re-searching.
Results are paged 25 at a time, so a large limit means several page loads.
Inputs: keywords (required), sort, limit, job_type, +5 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: searching jobs, fetching job details, reading profiles, and managing session state. No overlap between the data-access tools and the session-management tools.
All five tools follow a consistent 'linkedin_<verb>_<noun>' pattern (search_jobs, get_job, get_profile, check_session, close_session). The naming is uniform and predictable.
Five tools is well within the ideal range for a focused server. Every tool contributes to a clear workflow: session management, job search, job details, and profile lookup.
The server covers the core read workflows for LinkedIn jobs and profiles, but lacks profile search or listing capabilities. However, for its stated purpose (searching jobs and reading profiles), the surface is largely complete.
Maintenance
Related MCP Connectors
LinkedIn jobs, companies and people for AI agents, plus messages and invites via your own account.
LinkedIn for AI agents: search people, read profiles, posts and connections via a connected account
LinkedIn for AI agents: inbox, invitations, Sales Navigator search, posts, jobs, quotas, webhooks.
Give AI agents the LinkedIn tools to find, qualify, engage, and follow up with prospects.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI assistants to interact with LinkedIn by scraping profiles, companies, job postings, and getting personalized job recommendations using authenticated browser automation.1711,806 PyPI4,230Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to search, filter, and extract job listings from LinkedIn using an automated headless browser with semantic AI filtering and deduplication.28 npmMIT
- AlicenseAqualityBmaintenanceEnables AI agents to use an existing browser session to read profiles and companies, search jobs and people, and manage messages and connection requests on LinkedIn.21Apache 2.0
- AlicenseAqualityBmaintenanceGives AI agents access to LinkedIn through your own browser session, enabling profile and company research, job searching, and management of conversations and connection requests.25Apache 2.0