governed-mcp@0.1.0
VERIFIEDPublisher claims: "Sits in front of any other MCP server and decides, outside the model, whether each tool call goes straight through, waits for a named person to approve it, or is refused. Adds one-time approval claims, step-derived idempotency keys, read-after-write verification and a hash-chained audit log so agents can propose writes safely." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-06 and scored it 88/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
No other findings across 3,216 lines in 35 files.
Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.