Protect MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 17 Sep 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, 21 h ago · rules 3dff92dd89df
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 waySigned receipts and Cedar policies for AI agent tool calls. Claude Code hooks, MCP gateway.
Runtime verification for agent tool calls: Ed25519 signed receipts, fail-closed RCE/SSRF checks.
Governed 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.
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
Deterministic policy enforcement and MCP management for AI agent tool calls.
Protect MCP — questions
Answers built from our own checks of this server.