Security review

Is Kawa Code MCP safe to give an agent?

write capableneeds cautionwrite capablehealthy

A factual risk summary built from Kawa Code’s real tool surface, execution model, and verification history — not a vibe. Trust score 67/100.

01What it can do

Has tools that can create or modify data.

26 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 @kawacode/mcp`) — it pulls and executes third-party code; pin versions and review the source.

03Permissions & auth

Manage GitHub · writeMaps & location · writeKnowledge & memory · destructiveProcess payments · writeVersion control (git) · destructiveScrape a website · write

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

04Verification

handshakepassed — tool surface is real

runstools_list:passed · handshake:passed · metadata:passed · tools_list:passed · handshake:passed · metadata:passed · tools_list:passed · handshake:passed · metadata:passed · tools_list:passed

last_checked2026-08-21 05:08Z

sourcesOfficial MCP Registry [p1]

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