Proctor MCP server
Human oversight for AI agents: block a tool call on a verified human, with on-chain proof.
B83/100grade B
Adoption
Growing
0 stars35 downloads/wk
Reviews
Write oneNobody has reviewed Proctor yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Proctor tools (1)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
request_human_approvalBlock until a verified human who is NOT the operator of this agent approves or refuses a
Public scan report
scanner v0.1.5 · 2026-09-19 · same rubric, same numbers if you re-run it
no findings
- Code scan3 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 8 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Install directly
Runs npx -y proctor-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add proctor -- npx -y proctor-mcp
Proctor: common questions
- Is Proctor MCP server safe?
- Mostly: it is graded B (83/100). Read the Proctor safety report
- How do I install Proctor?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does Proctor need an API key?
- Yes. The registry entry asks for
HEDERA_AGENT_KEY. - Is Proctor maintained?
- The last commit was 10 days ago (2026-09-11). The latest release is v1.0.0.