Protect MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 26 Oct 2026.
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
What the code does
We read the source, 3 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
need(process.env.GITHUB_ACTIONS==='true'&&process.env.GITHUB_REPOSITORY===DEMO_REPOSITORY&&process.env.GITHUB_REF==='refs/heads/main'&&['workflow_dispatch','schedule'].includes(process.env.GITHUB_EVENT_NAME||''),'demo_trusted_workflow_required');
execSync(`docker rm -f ${sandbox.id} 2>/dev/null`, { stdio: 'pipe' });
import { appendFileSync, readFileSync, existsSync, readdirSync, statSync } from 'node:fs';
…toLowerCase().split('/').some(p=>p==='node_modules'||p==='.git'||p==='.github'||p==='.env'||p.startsWith('.env.')||p==='.npmrc'||p==='.yarnrc'||p==='.netrc')&&!/\.(pem|key|p12|pfx)$/i.test(path);}
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to Protect MCP
same job, measured the same wayGoverned USDC wallet for AI agents — policy gates, spending caps, and Ed25519-signed receipts.
Ed25519-signed market-state receipts for 28 exchanges. Fail-closed pre-trade gate.
Runtime verification MCP server: fail-closed checks for agent tool calls, signed evidence receipts.
Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
Fail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.
Policy-gated agent spend with signed receipts and rail-extract audit
Verifiable decision records for AI agents: signed receipts for calls to its own governed tools.
MCP gateway that checks each agent tool call against a signed grant and policy, and signs a receipt
Protect MCP — questions
Answers built from our own checks of this server.