Is Slack MCP safe to give an agent?

write capableneeds cautionbrokenbroken

A factual risk summary built from Slack’s real tool surface, execution model, and verification history — not a vibe. Trust score 27/100.

01What it can do

Has tools that can create or modify data.

8 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 npx (`npx -y @modelcontextprotocol/server-slack`) — it pulls and executes third-party code; pin versions and review the source.

03Permissions & auth

Send chat messages · write

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

04Verification

handshakenot confirmed

runshandshake:failed · metadata:failed · metadata:passed

last_checked—

sourcesunknown

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