Runs baseline and before/after verification trials in resource-limited, offline Docker Linux containers, isolating each test and mutation job.
Registers an exact Git repository root and verifies changes against a specified base commit, binding observations to source, dependency, policy, and image hashes.
Uses StrykerJS to perform changed-source mutation testing with a hard mutation cap, measuring which controlled edits the selected tests detect.
Runs selected offline Node-mode Vitest tests on the baseline and both implementations, with Vitest pinned and test names required to be unique in the registered scope.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ProofGate MCP Server verify my change against HEAD and report the pass/fail verdict plus mutation findings"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A change. Its evidence. Before/after tests and bounded mutation evidence for changes written with Claude Code, Codex or your editor.
Live demo · Türkçe · Setup · Architecture · Security · Contributing
An agent can fix a permission check and add a test that also passes on the broken code. ProofGate runs the same selected test on both implementations, then uses StrykerJS to measure which controlled edits the tests detect. Every observation is bound to exact source, dependency, policy and image hashes.
One baseline and three fresh before/after pairs in resource-limited offline Linux containers.
Changed-source mutation scope using StrykerJS/Vitest, with a hard cap before mutation execution.
Findings for removed mandatory tests, skip/only/todo, configuration changes and mutation exclusions.
Explicit pass, fail and inconclusive results. Crashes, timeouts, zero tests and incomplete work cannot establish a successful fix.
A real CLI, six-tool stdio MCP server, TR/EN review UI and downloadable reports.
Local use without an account; optional self-hosted teams with roles, invitations, expiring project tokens and operator recovery.
Core verification needs no model API key, paid service or cloud account. This is an MIT-licensed alpha; a policy pass covers the recorded checks, not general correctness or security.
Related MCP server: agent-eval-mcp
Use Node.js 24.15+ within the Node 24 line, npm, Git and a running Docker Linux engine. Windows uses Docker Desktop in Linux-container mode.
git clone https://github.com/nexora-studio-tr/proofgate.git
cd proofgate
npm run setup
npm startThe setup script installs locked dependencies with lifecycle scripts disabled, builds the app/runner, creates an editable example repository and prepares its dependencies. Open the private URL in .proofgate/launch-url. In the UI, choose Verify a change, leave the base as HEAD, freeze the plan and run it. The bundled permissions fix should pass with seven trials and ten detected mutations.
For your own project, register the exact Git root and a reviewed policy outside the candidate tree:
node dist/apps/cli/src/index.js register /absolute/repo --policy /absolute/policy.json
node dist/apps/cli/src/index.js doctor --build --project PROJECT_ID
node dist/apps/cli/src/index.js verify --project PROJECT_ID --base BASE_COMMITKeep the local server running. CLI and MCP use the same supervisor and queue. Start with the example policy and setup instructions. The initial adapter pins Vitest 5.0.5 and uses a trusted standalone Node test configuration. Test names must be unique in the registered scope.
With the server running, generate a complete local plugin package:
node scripts/connect.mjs codex --data .proofgate
node scripts/connect.mjs claude --data .proofgateThe printed folder contains the shared skill, project IDs and an absolute-path MCP configuration. The generator does not edit client settings or grant permissions. Legacy and modern MCP handshakes are tested. Plugin installation.
Open the public read-only demo. The Free instance can sleep when idle; the first request may take about a minute.
node dist/apps/cli/src/index.js demo --port 4328 --data .proofgate-demoThe read-only demo displays a recorded real execution of the bundled synthetic project. Visitors cannot upload code, run jobs or access team/admin data. It is separate from live verification of your repository. Reference evidence · Free Render deployment.
npm run check
npm run format:check
npm run test:docker -- --all
npm run test:isolation
npm run test:integration
npm run test:browser -- --start
npm run test:team-browser
npm run release:pack
npm run test:releaseExecution checks require Docker. Browser checks also need npx playwright install chromium (Linux CI uses --with-deps). Packaging uses an explicit source allowlist; runtime data, credentials, dependencies and sibling projects are excluded. Validation status.
Initial support is a single npm package, TypeScript/JavaScript and offline Node-mode Vitest tests. Source capture is capped at 500 files, 512 KiB per file and 4 MiB total. Public npm dependencies must be integrity-pinned; install scripts are disabled. Browser/E2E adapters, private registries, monorepos, SMTP, SSO/MFA and automatic fixes are outside this release. Docker shares a kernel; this is not unrestricted hostile-code hosting.
ReproPack is a separate project. No commercial Discord bot source is included.
This server cannot be deployed
MCP server for Superserve sandboxes: create, exec, and manage Firecracker microVMs
MCP server for visual regression testing: triage a PR's UI diffs from your coding agent.
Remote MCP server exposing your Node Command fleet (files, shell, processes, browser) to AI hosts.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
