MCP.so
Sign In

TruVerifAI Panel-review MCP ServerVerifiedFeatured

@TruVerifAI

Basic information

Category

AI & Agents

Last updated

License

MIT

Author

TruVerifAI

Submitted by

BD Partner

About TruVerifAI Panel-review MCP Server

TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g

#AI code review#code review#MCP server#AI coding agents#guardian agent#multi-model#pre-commit gates#developer tools#security#Claude Code#Cursor#Codex#git hooks#LLM

TruVerifAI Panel-review MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "truverifai": {
      "command": "npx",
      "args": [
        "@truverifai/init"
      ]
    }
  }
}

TruVerifAI Panel-review MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Panel Review?

TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions. Four frontier models from four different vendors (OpenAI, Anthropic, Google, xAI) argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, then return a structured verdict with severity-tagged findings. The findings live between the models: on hard cases no single model catches everything, so the disagreement between four independently trained models becomes the signal.

Because agents under deadline pressure skip optional reviews, a set of review gates runs locally on your machine and blocks the riskiest changes (auth, secrets, payments, destructive migrations, removed guards, and more) until a real review or an explicit logged override has happened. The gates are cooperative pause points, not a wall: they fail open on any error, and there is always a reachable exit.

What @truverifai/init does

@truverifai/init is the one-command installer for Panel Review. Run it once and it detects the AI coding agents on your machine (Claude Code, Codex, Cursor, Copilot, VS Code, Gemini CLI, Antigravity), signs you in through a browser device login, connects the review tools, and installs the local pre-commit and pre-write gates. It typically completes in under a minute and is fully undoable.

npx @truverifai/init          # detect agents, sign in, install gates + tools, verify
npx @truverifai/init doctor   # re-verify setup on demand

Key features

  • Four-vendor deliberation on designs, diffs, and commits, with cross-examination on the exact points where the models disagree.
  • Local review gates the agent cannot silently skip on high-risk changes, with a full release ladder for false positives and genuine exceptions.
  • Runs across eight certified agent surfaces; any other MCP client gets the tools plus a git pre-commit fallback.
  • Privacy by design: risk classification is 100% local, and what leaves your machine is a hashed fingerprint, content hashes, and category labels, never your source code or file paths.
  • Bring Your Own Keys and Bring Your Own Models: seat your own or self-hosted models alongside the frontier panel, or route inference through your own cloud account.

Open source and privacy

The client is open source and verifiable: the gates, the risk classifier, the skills, the platform bundles, and the npx @truverifai/init CLI are all MIT licensed, public at github.com/TruVerifAI/init, and published with zero runtime dependencies. The hosted service that runs the four-model panel is proprietary. TruVerifAI never trains models on your code or your content.

Demos

Links

Comments

More AI & Agents MCP servers