Security review

Is linkedin-mcp-server MCP safe to give an agent?

write capableneeds cautionwrite capablehealthy

A factual risk summary built from linkedin-mcp-server’s real tool surface, execution model, and verification history — not a vibe. Trust score 51/100.

01What it can do

Has tools that can create or modify data.

19 tools observedwrite present

02Execution model

Runs locally over stdio — the server process executes on your machine with your user's privileges. Vet the source and package before granting access.

Installs via uvx (`uvx mcp-server-linkedin@latest`) — it pulls and executes third-party code; pin versions and review the source.

03Permissions & auth

Send chat messages · writeSocial selling & outreach · write

The write/destructive access this server can exercise, inferred from its verified tools.

04Verification

handshakenot confirmed

runshandshake:failed · metadata:passed · handshake:failed · metadata:passed · handshake:failed · metadata:passed · handshake:failed · metadata:passed · handshake:failed · metadata:passed

last_checked2026-08-16 21:22Z

sourcesGitHub repo search [p4]

Reduce the risk

Worried about handing an agent raw access? See governed agents in action — Apex gives your AI paced, capped, fully-logged hands with approval queues before anything runs.

Explore Apex →

See also: full server page · setup · alternatives