# Verificate MCP (slim)

> Verificate MCP, an MCP server by verificate.ai, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Agentic code review, no signup to try: reality gates + frontier-model review, with veto.

- Full: https://www.anchorterminal.com/tools/verificate-mcp.md (~800 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/tools/verificate-mcp.json · canonical https://www.anchorterminal.com/tools/verificate-mcp
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

# Verificate MCP

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by verificate.ai (https://verificate.ai/mcp)
- Listed because: It's published in the registry under verificate.ai, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Agentic code review, no signup to try: reality gates + frontier-model review, with veto.

## Facts

- MCP registry: `ai.verificate/mcp` 1.8.7
- Endpoint: https://mcp.verificate.ai/mcp (streamable HTTP)
- Source: https://github.com/Verificate-Dev/verificate-mcp-quickstart
- Website: https://verificate.ai/mcp
- GitHub stars: 1
- Registry entry updated: 2026-08-01

## Tools

- Tools it lists (5, about 2,858 tokens of context, `tools/list` without credentials, checked 2026-10-04 22:20 UTC):
  - `validate_artifact` (read-only): Deterministic production-readiness gate for AI-built systems. Verifies the invariants that stop a system silently shipping broken: every critical component is…
  - `validate_ai_output` (read-only): The merge gate for ANY AI-written output — code, documentation, reports, emails, configs: returns a binary approve/reject verdict with veto power — e.g. it…
  - `validate_plan` (read-only): The gate for PLANS, designs and specs — run BEFORE any code is written, the cheapest place to catch a bad design. Returns the same binary verdict shape as…
  - `analyze_code` (read-only): Advisory deep-dive on existing code — scores and findings, deliberately NO pass/fail verdict, so it never blocks an agent. Surfaces performance hot paths,…
  - `generate_code` (read-only): Generate code and gate it in one step: an LLM writes the implementation, then the same protection engine as validate_ai_output vets it — retrying generation…
- How its tools read to an agent (0 errors, 2 warnings, 1 note, about 2,858 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - warn TC13 validate_artifact: artifact (object with no properties)
  - warn TC13 validate_plan: context (object with no properties)
  - note TC24 server: 1 of 5 tools have no outputSchema

- JSON: https://www.anchorterminal.com/api/v1/tools/verificate-mcp.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming