MCP Server for LinkedIn — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Track package and LinkedIn API changes because platform authentication can change

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Authenticated LinkedIn research, profile/job search and messaging workflows.

What we know

This MCP server automates LinkedIn through an authenticated browser session, exposing people/company/job research and selected messaging/networking actions.

Maintenance / activity evidence

Observed Oct 5, 2026 (UTC)fix(browser): Restart a browser that stopped ( 1240)

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Activity source · commits ↗Activity source · releases ↗

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Can access and act through the authenticated account. Writes: Send messages; Send connection requests.
Relies on LinkedIn account/session authentication.
Sensitive access: LinkedIn account session, Private messages, Profile/network data

The server acts inside an authenticated LinkedIn account and can send external communications; use a dedicated scope and require confirmation for writes.

Security source · repository notice ↗

Full authority, access and evidence limits are available in Review context and Access & risk.

Popularity

3,762 repository stars · 68.3k package downloads / 30 days

Stars observed Oct 6, 2026. Downloads observed Oct 6, 2026.

All limitations / Review context

Which LinkedIn operations and authentication requirements are currently supported?

The bounded assessment reviewed the official README, repository notices, security policy path, and security page for known material public-tracking blockers. No such blocker was identified. This is a public-tracking assessment, not an installation safety certification.

The server acts inside an authenticated LinkedIn account and can send external communications; use a dedicated scope and require confirmation for writes.
Can access and act through the authenticated account.
Relies on LinkedIn account/session authentication.
Profile, job and message data may be exposed to the connected AI client.
Reviewed write actions: Send messages; Send connection requests
Sensitive access: LinkedIn account session, Private messages, Profile/network data
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
A project-specific SECURITY.md policy was not available at the fetched official path; the review remains limited to published repository notices.
No installation, runtime, client matrix, or complete tool-contract audit was performed in this review.
The fetched official SECURITY.md path returned HTTP 404; it was not treated as positive evidence.
Requires an authenticated LinkedIn session.
LinkedIn UI/account restrictions can break or constrain automation.
This is not an official LinkedIn MCP.

Original activity observations

2026-10-05T16:48:12Z: fix(browser): Restart a browser that stopped ( 1240)

Technical identity

github.com/stickerdaniel/linkedin-mcp-server

Exact implementation source: https://github.com/stickerdaniel/linkedin-mcp-server ↗
Reviewed resource type: MCP Server
Repository identity: stickerdaniel/linkedin-mcp-server
Package identity: pypi:mcp-server-linkedin

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 6, 2026

GitHub repository ↗
stickerdaniel/linkedin-mcp-server
Recorded repository material and project history.
Evidence source ↗
pypi.org/project/mcp-server-linkedin/
Source material retained for this review.
Includes references whose attribution is not established.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
LinkedIn MCP Server uses a local stdio package; login modes need careful consent.
publisher setup entry · Publisher instructions · Review before use
```
uvx mcp-server-linkedin@latest
```
Configure / authenticate
MCP100 setup guide
Register command uvx with args ["mcp-server-linkedin@latest"] and optional UV_HTTP_TIMEOUT=300. Follow official package authentication directions; do not paste LinkedIn cookies into published examples.
Check connection
Suggested check
List server tools in client; avoid scraping a real personal account as verification.
Remove / uninstall / revoke
MCP100 setup guide
Remove the installed LinkedIn MCP entry in Claude/Codex/Cursor using the client registration name you chose, and delete only its optional local browser/session cache if documented for your installation. Revoking LinkedIn access, if used, is a separate action. Client remove command is an MCP100 composed example: replace the registration name with your actual installed name.
Client unregistration, program uninstall, persistent-data deletion, and credential revocation must be treated separately.
Previously reviewed local logout; provider revocation is separate: Publisher `--logout` clears stored MCP session only.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove linkedin

Official Documentation & Sources

What it does

This MCP server automates LinkedIn through an authenticated browser session, exposing people/company/job research and selected messaging/networking actions.

Capability: Communication
Resource type: MCP Server
Industry: Human Resources
Best fit: Authenticated LinkedIn research, profile/job search and messaging workflows.

Representative uses

Search people, companies and jobs
Read profiles
Read and send messages
Send connection requests

Limitations

Requires an authenticated LinkedIn session.
LinkedIn UI/account restrictions can break or constrain automation.
This is not an official LinkedIn MCP.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Relies on LinkedIn account/session authentication.
Permissions: Can access and act through the authenticated account.
Data handling: Profile, job and message data may be exposed to the connected AI client.
Cost: free
Risk and cautions: The server acts inside an authenticated LinkedIn account and can send external communications; use a dedicated scope and require confirmation for writes.

Access scope and cautions

Write actions: Send messages Send connection requests
Sensitive access: LinkedIn account session Private messages Profile/network data
Risk level: high

FAQ

Based on reviewed evidence as of 2026-10-06. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Search people, companies and jobs; Read profiles; Read and send messages; Send connection requests.

What setup and authentication are documented?

Recorded installation/entrypoint step: uvx mcp-server-linkedin@latest. Recorded transport: stdio, streamable_http. Prerequisites: uv; LinkedIn account/session. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Uses an authenticated LinkedIn browser/session context.

Can it modify data or perform write operations?

Documented write actions include: Send messages; Send connection requests. Recorded permission boundary: Can access and act through the authenticated account.

What data-handling boundary should I consider?

Profile, job and message data may be exposed to the connected AI client. Recorded sensitive-access context: LinkedIn account session; Private messages; Profile/network data.

What limitations and risks should I check before use?

The server acts inside an authenticated LinkedIn account and can send external communications; use a dedicated scope and require confirmation for writes. Requires an authenticated LinkedIn session. LinkedIn UI/account restrictions can break or constrain automation. This is not an official LinkedIn MCP. A project-specific SECURITY.md policy was not available at the fetched official path; the review remains limited to published repository notices.

Is this an official MCP?

Daniel Sticker is listed as Community implementation in MCP100’s current evidence.