Verificate MCP

ai.verificate/mcpVersion 1.9.0

Merge gate for AI-written code: deterministic vetoes plus a Claude Haiku 5.5 review. No signup.

Status

Responds831 msNov 14, 2026, 13:34 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 13:34 UTC
Latency: 831 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 22:14 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://mcp.verificate.ai/mcpResponds831 msNov 14, 2026, 13:34 UTC

No sign-in

Claude Code

claude mcp add --transport http verificate https://mcp.verificate.ai/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: verificate
Remote MCP server URL: https://mcp.verificate.ai/mcp

Cursor

{
  "mcpServers": {
    "verificate": {
      "url": "https://mcp.verificate.ai/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"verificate","type":"http","url":"https://mcp.verificate.ai/mcp"}'

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

5 tools

Tools of Verificate MCP
	Description		Read-only	Idempotent	Open world
`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, reliability gaps and tech debt with concrete latency/throughput arithmetic (e.g. 'O(n²) dedup: ~4s at 10k items'). Read-only: the code is analyzed, never executed. Use it to understand a validate_ai_output rejection or review inherited code; use validate_ai_output when you need an accept/reject decision.	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, reliability gaps and tech debt with concrete latency/throughput arithmetic (e.g. 'O(n²) dedup: ~4s at 10k items'). Read-only: the code is analyzed, never executed. Use it to understand a validate_ai_output rejection or review inherited code; use validate_ai_output when you need an accept/reject decision.	No	Yes	Yes	Yes
`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. If every attempt is vetoed you still receive the last attempt, clearly marked validated:false with the gate findings — rejected code is never presented as clean. Generation runs on our infrastructure; nothing executes in your environment.	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. If every attempt is vetoed you still receive the last attempt, clearly marked validated:false with the gate findings — rejected code is never presented as clean. Generation runs on our infrastructure; nothing executes in your environment.	No	Yes	No	Yes
`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 nonexistent stripe.Inventory API, an N+1 loop with the latency arithmetic to prove it, or a doc claiming success with no evidence. Deterministic checks (mock/placeholder veto, reward-gamed tests, standard-library calls that do not exist, secrets written to logs) run first and cannot be overridden; a Claude Haiku 5.5 review (ISO/IEC 25010, ISO/IEC 5055) then verifies third-party API calls and scores quality, accuracy, reliability and tech debt; its high/critical security and API findings block. In a benchmark, a frontier model reviewing alone caught reward-gaming and hallucinated APIs 0/6 times in a natural review workflow; this gate checks for both on every call. Read-only: nothing is executed. Call it on every AI-generated deliverable before accepting it; use validate_plan for plans, analyze_code for an advisory report without a verdict.	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 nonexistent stripe.Inventory API, an N+1 loop with the latency arithmetic to prove it, or a doc claiming success with no evidence. Deterministic checks (mock/placeholder veto, reward-gamed tests, standard-library calls that do not exist, secrets written to logs) run first and cannot be overridden; a Claude Haiku 5.5 review (ISO/IEC 25010, ISO/IEC 5055) then verifies third-party API calls and scores quality, accuracy, reliability and tech debt; its high/critical security and API findings block. In a benchmark, a frontier model reviewing alone caught reward-gaming and hallucinated APIs 0/6 times in a natural review workflow; this gate checks for both on every call. Read-only: nothing is executed. Call it on every AI-generated deliverable before accepting it; use validate_plan for plans, analyze_code for an advisory report without a verdict.	No	Yes	Yes	Yes
`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, the import closure resolves (nothing assumed 'already on the box'), all runtime dependencies are declared, and health is a REAL fail-closed check. Returns approve/reject with a fix plan and ISO 27001 / ISO 5055 control evidence. Facts are gathered by the Verificate collector in your CI; the gate is the authority. Non-bypassable, fails closed. This is the control-plane sibling of validate_ai_output — code quality is one invariant; this gates the whole deployable.	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, the import closure resolves (nothing assumed 'already on the box'), all runtime dependencies are declared, and health is a REAL fail-closed check. Returns approve/reject with a fix plan and ISO 27001 / ISO 5055 control evidence. Facts are gathered by the Verificate collector in your CI; the gate is the authority. Non-bypassable, fails closed. This is the control-plane sibling of validate_ai_output — code quality is one invariant; this gates the whole deployable.	No	Yes	Yes	No
`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 findings on completeness, feasibility, performance and scalability implications, security risks and missing considerations (e.g. it rejects a plan that polls an API every 100ms per client, with the request-volume math). Read-only: nothing is executed or stored beyond the verdict. Use validate_ai_output for the code that follows.	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 findings on completeness, feasibility, performance and scalability implications, security risks and missing considerations (e.g. it rejects a plan that polls an API every 100ms per client, with the request-volume math). Read-only: nothing is executed or stored beyond the verdict. Use validate_ai_output for the code that follows.	No	Yes	Yes	Yes

Details

Registry status: Active
Published: Nov 10, 2026
Updated: Nov 10, 2026
Website: https://verificate.ai/mcp⁠ (opens in a new tab)
Repository: https://github.com/VerificateAI/verificate-mcp-quickstart⁠ (opens in a new tab)
Categories (suggested): AI modelsSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing