Categories › Software Development › Testing & QA
Merge gate for AI-written code: deterministic vetoes plus a Claude Haiku 5.5 review. No signup.
Remote server: your requests and data go to mcp.verificate.ai. Claude Code: claude mcp add --transport http verificate-mcp https://mcp.verificate.ai/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
validate_artifact — Deterministic production-readiness gate for AI-built systems. Verifies the invariants that stop a system silently shipping broken: every crivalidate_ai_output — The merge gate for ANY AI-written output — code, documentation, reports, emails, configs: returns a binary approve/reject verdict with veto 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 veanalyze_code — Advisory deep-dive on existing code — scores and findings, deliberately NO pass/fail verdict, so it never blocks an agent. Surfaces performagenerate_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 — retNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.