MCP serverai.verificate/mcp

Agentic code review, no signup to try: reality gates + frontier-model review, with veto.

UNRATEDActivestreamable-httpmcp.verificate.ai

Overview

Score?

UNRATED 0.652

of what a free look can see, on 31 looks

Looks

last 12 hr ago

Tools

changed 13 days ago

URL

mcp.verificate.ai/mcp

streamable-http

Says it is

verificate-mcp-http 1.2.0

protocol 2024-11-05

In the record since

32 days ago

0median 0.606 · this server 0.652 · highest on record 0.8561

The tools this server lists, read out of the definition it returned
Tool	Schema
analyze_code Advisory deep-dive on existing code — scores and findings, deliberately NO pass/fail verdict, so it never blocks an agent. Surfaces performance hot paths, scalability cliffs, relia	input · output
generate_code 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 when the gate rejects.	input · output
validate_ai_output 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 rejects code calling the	input · output
validate_artifact Deterministic production-readiness gate for AI-built systems. Verifies the invariants that stop a system silently shipping broken: every critical component is PRESENT and LOADS, th	input · no output
validate_plan 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 validate_ai_output, with	input · output

Verify it yourselfnpx teppi-check https://mcp.verificate.ai/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ23AJ0FZNZXPBR4RT88EG