How do I use linkedin-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. 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.

de en es ja ko ru zh

linkedin-mcp

by TSS99

Overview Schema Related Servers Score Discussions

Python

Local

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
`linkedin_search_jobs`	Listings with title, company, location, workplace type, salary when posted, posted age, and `job_id`. Filters: location, posted-within-days, experience level, job type, workplace type, Easy Apply, sort order.
`linkedin_get_job`	One posting in full — company, location, LinkedIn's job insights, and the whole description with the "See more" clamp expanded.
`linkedin_get_profile`	Name, headline, location, about text, experience history, education and skills.
`linkedin_check_session`	Whether the saved browser session is still signed in.
`linkedin_close_session`	Detaches from Chrome, leaving the window and session alone.

Related MCP server: LinkedIn MCP Server

Install

Requires Python 3.12+, uv, and Google Chrome.

git clone https://github.com/TSS99/linkedin-mcp.git
cd linkedin-mcp
uv sync

Sign 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 --login

The 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=system

or 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 pytest

The 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 tools

linkedin_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.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.3/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the behavioral burden. It states the check itself but does not explicitly confirm it is non-mutating or describe the return format. The login-wall context implies safety, but the description lacks explicit boundary details. It does not contradict anything, but could be more transparent about side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler. The purpose is stated first, and the second sentence adds valuable context about why this tool matters. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless check with no output schema, the description fully covers what an agent needs: what the tool does and why it's important before other tools. It is complete and self-sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and the schema is already complete (100% coverage). Baseline is 4. The description adds no parameter information, which is appropriate since there are none to document.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states a specific verb ('check') and resource ('whether the browser is signed in to LinkedIn'). The description distinguishes it from sibling tools by its unique purpose—session verification—and adds context about the login wall, making it unambiguous what this tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states that 'every other tool needs this to be true,' implying it should be called before other LinkedIn operations. This provides clear usage context. It does not list exclusions or alternatives, but given its singular nature, the guidance is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

linkedin_close_sessionA

Disconnect from the browser and free resources.

This detaches from Chrome; it leaves the window and the saved session alone.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It transparently discloses the key side effect: it does NOT close the window or the saved session, and it indicates resource freeing. This goes beyond a simple 'close session' and prevents the agent from assuming destructive behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with zero waste. The core action is front-loaded, and the clarifying sentence adds essential side-effect information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless tool with no output schema, the description is sufficient. It covers what it does and what it doesn't do. One could add typical usage timing (e.g., 'call at end of session'), but that is minor and not strictly necessary for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so schema coverage is trivially 100%. The description adds no parameter meaning because none exist; per rubric, a baseline of 4 is appropriate for a parameterless tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Disconnect from the browser and free resources.' It further clarifies by specifying it detaches from Chrome and leaves the window and saved session intact, distinguishing it clearly from the search/get/check siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no explicit when-to-use or when-not-to-use guidance. It does not mention that it should be used after other LinkedIn operations or contrast itself with linkedin_check_session. The implication is present but not stated, leaving the agent to infer usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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.

ParametersJSON Schema

Name	Required	Description	Default
`job`	Yes	Job id, or a /jobs/view/<id> LinkedIn URL

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must bear the burden. It discloses the output content, including the 'See more' clamp expansion, which is a concrete behavior. However, it does not mention prerequisites like authentication needs, rate limits, or error behavior. For a read operation, this is acceptable but not exhaustive, so a 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two efficient sentences. The first states the overall purpose, and the second lists the return fields with the clamp expansion noted. No fluff, front-loaded key info, and every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description lists the return values in detail, providing adequate information for an agent to know what to expect. It does not cover prerequisites like active sessions (sibling check_session exists) or error cases, but for a simple GET with clear return fields, it is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the single parameter, already specifying it accepts a job ID or URL. The description itself does not add additional semantics beyond what the schema provides. Baseline 3 is correct given the schema's completeness.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves full details for a single job posting and enumerates the exact fields returned (title, company, location, posted age, insights, complete description). This verb+resource focus distinguishes it from siblings like search, profile, and session tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage: it requires a job ID or URL to retrieve full details. The context is clear that this is for a single job, not searches or profiles, but it does not explicitly mention when not to use it or name alternatives. Still, for a straightforward GET tool, the usage context is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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.

ParametersJSON Schema

Name	Required	Description	Default
`profile`	Yes	Profile slug, e.g. 'satyanadella', or a full /in/<slug> URL
`include_sections`	No	Include about, experience, education and skills

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It transparently discloses the return content and the page-load trade-off, but omits any session/auth prerequisite or error behavior. This is partially transparent but not comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three terse sentences, each earning its place: purpose, returns, and the parameter trade-off. The essential information is front-loaded with zero fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only profile tool with no output schema, the description covers what's returned and the parameter option. It omits explicit session requirements, but sibling tools (check_session/close_session) imply that context, so it's not a critical gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are documented. The description adds value for include_sections by explaining the decision rule and its result-size impact, and reinforces the profile format. This exceeds the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear verb-resource pair ('Read a LinkedIn profile') and then lists the specific fields returned (name, headline, location, about, experience, education, skills). This unambiguously distinguishes it from sibling job-search and session tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The purpose is explicit, and the include_sections guidance gives a concrete conditional ('Set include_sections to false when you only need to confirm who someone is') with a performance trade-off. It doesn't explicitly contrast with siblings, but the domain is distinct enough that this is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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.

ParametersJSON Schema

Name	Required	Description
`sort`	No	Order: 'date' or 'relevance'
`limit`	No	Maximum number of results
`job_type`	No	One of: full-time, part-time, contract, temporary, internship, volunteer, other
`keywords`	Yes	Search keywords, e.g. 'machine learning engineer'
`location`	No	City, region or country, e.g. 'Bengaluru' or 'India'
`easy_apply`	No	Restrict to Easy Apply listings
`workplace_type`	No	One of: on-site, remote, hybrid
`experience_level`	No	One of: internship, entry, associate, mid-senior, director, executive
`posted_within_days`	No	Only jobs posted within this many days

TDQS

A4.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses that results are paged 25 at a time and that salary may be absent, but it does not mention authentication/session requirements or rate limits. With no annotations provided, the description carries the full burden, and the existence of linkedin_check_session suggests a session prerequisite that is not mentioned. This is a notable gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is about 100 words, front-loaded with the main purpose, and the second paragraph covers pagination. It avoids redundancy and each sentence contributes value, such as noting the paging limit and the alternative tool. No fluff or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains the return fields and pagination, and guides to linkedin_get_job, which covers essential operational details. However, it does not mention prerequisites like an active LinkedIn session (implied by check_session sibling) or error/edge-case behavior. Given the parameter count and no output schema, the description is fairly complete but misses these key operational aspects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides 100% description coverage for all 9 parameters, so the schema already documents their meaning. The description does not add additional parameter semantics beyond what the schema offers (e.g., it does not clarify how sort values map to behavior or the exact format of location). Baseline 3 is appropriate given the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches LinkedIn job listings, and explicitly distinguishes itself from the sibling linkedin_get_job by instructing to pass the returned job_id to that tool for full descriptions. This separates purpose from the retrieval sibling without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells the agent to use linkedin_get_job for the full description rather than re-searching, which is a clear directive about when to use an alternative. It also implicitly distinguishes from profile/session tools by focusing on job search, so usage context is evident.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

5 tool updatesv0.1.0Aug 27, 2026
- First observedlinkedin_check_session
- First observedlinkedin_close_session
- First observedlinkedin_get_job
- First observedlinkedin_get_profile
- First observedlinkedin_search_jobs

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.3/5.0

Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count5/5

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.

Completeness4/5

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

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

SalesTouchOAuth
io.salestouch
Give AI agents the LinkedIn tools to find, qualify, engage, and follow up with prospects.
Social Media CRM Autonomous Agents
22
ZOOQ - LinkedIn Data for AI Agents A
io.github.baldiga
Live LinkedIn data for AI agents: profiles, companies, jobs, posts, email finding. No account risk.
Social Media Search Research & Data
451
crispyOAuth
sh.crispy
Full LinkedIn access for AI agents: leads, messaging, and campaigns with safe limits built in.
Social Media CRM Communication
2
LinkedNavOAuth
io.github.linglistack
Run LinkedIn outreach from your AI chat: find leads, launch campaigns, send, and reply.
CRM Social Media
1

Related MCP Servers

LinkedIn MCP Server
Web Scraping Browser Automation Social Media
stickerdaniel
A
license
A
quality
A
maintenance
Enables AI assistants to interact with LinkedIn by scraping profiles, companies, job postings, and getting personalized job recommendations using authenticated browser automation.
Updated 11 hours ago (2026-09-05 20:59 UTC)
17
3,352
Apache 2.0
LinkedIn MCP Server
Web Scraping Browser Automation Social Media
eliasbiondo
A
license
A
quality
F
maintenance
Enables searching and scraping of LinkedIn for structured data on people, companies, and job listings. It allows AI clients to retrieve detailed profiles, experience, and activity sections using browser automation.
Updated 6 months ago (2026-03-08 19:55 UTC)
7
182
MIT
LinkedIn Job Scraper MCP
Browser Automation Web Scraping
Anjani27
A
license
Not graded
quality
B
maintenance
Enables AI assistants to search, filter, and extract job listings from LinkedIn using an automated headless browser with semantic AI filtering and deduplication.
Updated 2 months ago (2026-06-29 11:31 UTC)
25
MIT
LinkedIn MCP Server
Social Media Communication
Sabari2005
A
license
A
quality
B
maintenance
Lets an AI assistant operate LinkedIn through an authenticated browser session, enabling profile management, posting, networking, messaging, job search, and automated applications.
Updated 11 days ago (2026-08-26 11:31 UTC)
100
363
1
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/TSS99/linkedin-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server