
Take your vibe-coded MVP all the way to production — 17 reality gates + frontier-model review with
Take your vibe-coded MVP all the way to production — 17 reality gates + frontier-model review with veto power on every AI-written change. Hosted MCP; free to try, no signup.
·
Real output from the live server: 12 lines of AI-written payment code — rejected, fixed, approved, in seconds.
You vibe-coded the demo. This ships it. Between a working demo and a launched product used to stand an experienced CTO and a senior dev team — the people who catch the mock refund path, the invented SDK call, the loop that dies at real traffic. Verificate MCP is that review team as an MCP server: deterministic veto checks (placeholders and mocks, reward-gamed tests, invented standard-library APIs, secrets written to logs, deceptive or evidence-free claims), then a Claude Haiku 5.5 review against ISO/IEC 25010 and ISO/IEC 5055, run on every AI-written change before it reaches your codebase. Every verdict comes with a receipt. The AI writes; the gate holds the bar; you ship. Hosted, zero-install, binary verdict in seconds — in Claude Code, Cursor, Windsurf or any MCP client.
Not another linter wrapper. The code-quality shelf on every MCP directory is two things: scanners (ESLint, Semgrep and SonarQube bridges — deterministic rules, no judgment) and prompt relays that pipe your repo to your own LLM key (self-review with extra steps). Verificate is neither: its deterministic checks hold a veto that no model output can override.
Your coding assistant writes a mock and calls it done. It invents an SDK call that doesn't exist. It ships an N+1 loop that passes every test and dies under load. Verificate MCP runs the deep review pass on every AI output — deterministic reality gates first (any one can veto), then an enterprise-grade review scores what survives — before the code reaches your codebase.
os.read_text). Third-party SDK calls are checked by the model review.decision, the model's unmodified opinion beside it, and a receipt: input and prompt hashes, prompt and policy versions, the model, whether the review was complete, and what was not verified. A review that cannot cover the scope says so and is never an approval.12 plausible lines of AI-written payment code were sent through the production gateway. Verdict: REJECTED — score 30.8/100, vetoed by code_reality_gate, with findings including:
"N+1 synchronous API calls … For 100 items, this results in 100 sequential HTTP roundtrips, taking ~10–20 seconds and blocking the event loop/worker thread … will trigger Stripe rate limiting (100 req/sec limit)." "
stripe.Inventoryis not a valid Stripe SDK resource." "Floating-point representation issues lead to rounding errors in financial transactions; Stripe API requires integer cents."
Each of those is an afternoon of production debugging, caught in seconds.
A frontier model asked "is this OK to merge?" in a natural workflow missed reward-gaming (a test
that only does assert True) and a hallucinated API (stripe.Refund.create_partial) in 0 of 6
runs each. Verificate's gate caught both 6 of 6, with 0 false positives on clean code. The
reward-gamed test is a deterministic veto; the invented third-party SDK call was caught by the model
review stage.
| Adversarial case | LLM review alone | Verificate gate |
|---|---|---|
Reward-gaming (assert True test) | 0 / 6 | 6 / 6 |
| Hallucinated API (nonexistent SDK call) | 0 / 6 | 6 / 6 |
That benchmark is from September 2026. The November frozen A/B (36 reviews, 6 unsafe approvals → 0)
is in BENCHMARK_2026-11.md. Reproduce the September run: scripts/ ·
full write-up: COMPARISON.md.
Each tool has one job — three gates that return verdicts, one advisor that doesn't, one generator:
| Tool | Job | Returns |
|---|---|---|
validate_ai_output | The merge gate for AI-written code and documents. Deterministic veto checks (placeholders and mocks, reward-gamed tests, invented standard-library APIs, secrets in logs) run first and can't be overridden; a Claude Haiku 5.5 review (ISO/IEC 25010, ISO/IEC 5055) then checks the rest, including third-party API calls. | One decision (approved / approved with conditions / rejected / incomplete) + severity-ranked findings + a receipt |
validate_plan | The gate for plans and designs, before any code exists — completeness, feasibility, scalability implications, risk. The cheapest place to catch a bad design. | Binary approve/reject verdict + findings |
validate_artifact | The gate for a deployable: every critical component present and loading, imports resolving, dependencies declared, health checks that really fail closed. | Binary approve/reject verdict + fix plan |
analyze_code | Advisory deep-dive on existing code — hot paths, rate-limit math, failure modes, tech debt. Use it to understand a rejection or review inherited code. | Scores + findings, deliberately no verdict |
generate_code | Generate + gate in one step — the LLM writes it, the same checks vet it before you see it. | Gated code, with the verdict |
The server also ships prompts and resources for a richer client experience:
gate_my_changes / review_my_plan — one-click workflows that loop validate → fix → re-validate until approved.verificate://gates (each deterministic check, the model review stage, and what is not run on the hosted gate) and verificate://example-verdict (a verbatim production rejection).Every machine gets 100 free validations — no account, no card, no key. Add the URL and go:
Claude Code
claude mcp add --transport http verificate https://mcp.verificate.ai/mcpOr install it as a Claude Code plugin (adds the MCP server and the verificate skill, so Claude gates its own work before presenting it):
/plugin marketplace add VerificateAI/verificate-mcp-quickstart
/plugin install verificate@verificateCursor / VS Code — one-click install:
LM Studio and Goose one-click buttons are at https://verificate.ai/mcp (GitHub strips their custom-protocol links).
Windsurf / any MCP client (JSON)
{
"mcpServers": {
"verificate": {
"url": "https://mcp.verificate.ai/mcp",
"transport": "http"
}
}
}Cursor: ~/.cursor/mcp.json. Windsurf: ~/.codeium/windsurf/mcp_config.json.
Then ask your assistant to "validate this function with verificate" — a structured verdict comes back in seconds (typically 5–25 s).
Cursor plugin — this repo is also a Cursor plugin (.cursor-plugin/plugin.json + mcp.json). The optional VERIFICATE_TOKEN variable can stay empty for the free tier.
OpenAI Codex — add the server in ~/.codex/config.toml:
[mcp_servers.verificate]
url = "https://mcp.verificate.ai/mcp"A packaged Codex/ChatGPT plugin (no auth headers, logo, skill) is in plugins/codex/.
Google Antigravity — add to Antigravity's mcp_config.json (Streamable HTTP):
{
"mcpServers": {
"verificate": { "serverUrl": "https://mcp.verificate.ai/mcp" }
}
}The Gemini CLI / Antigravity extension installs the same server.
Devin — add a custom MCP server in Devin's MCP settings: transport HTTP (Streamable), URL https://mcp.verificate.ai/mcp, authentication None (or Auth Header Authorization: Bearer <token> once you have a token).
IBM Bob — add to Bob's mcp.json:
{
"mcpServers": {
"verificate": { "type": "streamable-http", "url": "https://mcp.verificate.ai/mcp" }
}
}Sign up at https://verificate.ai/auth/signup (30-day trial, no card — then $30/mo) and add your token to the same config:
claude mcp add --transport http verificate \
https://mcp.verificate.ai/mcp \
--header "Authorization: Bearer YOUR_TRIAL_TOKEN"or in the JSON config add "headers": { "Authorization": "Bearer YOUR_TRIAL_TOKEN" }.
Tools an agent may call are tools it will skip under pressure. Add a standing rule (Claude Code: CLAUDE.md; Cursor: a rule file):
Before presenting any substantive code change as complete:
1. Call validate_ai_output on the change.
2. If the verdict is REJECTED, fix the findings and re-validate.
3. Never claim tests pass or systems are deployed without proof.One-paste setup prompts that install these rules for you: PROMPTS.md. Or wire it into CI as a merge gate — see examples/.
AI output ──► Deterministic veto checks (same input, same result)
• mock/placeholder presented as done
• reward-gamed tests
• invented standard-library APIs
• secrets written to logs (CWE-532)
• deceptive or evidence-free claims
│
▼
Claude Haiku 5.5 review (ISO/IEC 25010 + ISO/IEC 5055)
security · reliability · performance · maintainability
third-party API reality · high/critical L0/L2 findings block
│
▼
One decision + findings + receipt
(rejected = agent fixes findings and re-validates;
incomplete = the review could not cover the scope, never an approval)The two stages are deliberately separate: if reality and quality were blended into one score, a beautifully structured function that fakes its refund path could still average out to "acceptable." A veto architecture makes that impossible.
Everything else on the MCP code-quality shelf is free — and that's fair, because a wrapper should be free. What you can't get for free is judgment with authority:
| What you'll find on the directories | What it is | What it structurally can't do |
|---|---|---|
| Linter wrappers — ESLint MCP, Semgrep MCP, SonarQube MCP | Rule-based scanners exposed as MCP tools. Deterministic, free, worth running. | No judgment. Rules can't know the refund function never calls the payment provider, or that stripe.Inventory doesn't exist. No verdict, no veto — findings your agent is free to ignore. |
| BYO-key review relays | Your repo + a review prompt, piped to your own OpenAI/Anthropic key. | Self-review with extra steps: the reviewer shares the generator's blind spots, there are no deterministic gates underneath, and whatever the model says goes. You maintain keys, versions and hosting. |
| A bigger model | Hope the generator reviews itself better. | Self-review inherits self-blindness. An external gate holds the same bar for every model — which also makes smaller, cheaper models safe to ship with: same gate either way. |
| Human review of every AI diff | The gold standard, at human speed. | Doesn't scale at AI generation speed. The gate does the first pass in seconds; humans review verdicts, not raw diffs. |
| Verificate MCP | Deterministic checks with veto, then a Claude Haiku 5.5 review — fused into one decision with a receipt. Hosted. | — |
That second layer is the part you pay for: a model doing the deep review — production arithmetic, failure modes, SDK reality — with a deterministic floor under it that the model itself cannot argue away.
This repo is also a runnable, zero-dependency MCP server: a stdio bridge that serves initialize/tools/list locally and forwards tool calls to the hosted gateway. Use it with clients that prefer stdio servers:
VERIFICATE_TOKEN=<your-token> npx github:VerificateAI/verificate-mcp-quickstartOr with Docker:
docker build -t verificate-mcp .
docker run -i -e VERIFICATE_TOKEN=<your-token> verificate-mcpWithout VERIFICATE_TOKEN, tool calls use the free tier (100 validations, no signup).
Does it slow the agent down? Each validation takes seconds, inside the loop, before work is presented. Compare with a defect found in CI or production plus the context switch to fix it — gating is net-faster for any change that matters.
Which languages? Validation is language-agnostic; analysis covers mainstream languages (Python, JS/TS, C++, SQL, Swift, …). Pass context.language for best results.
Can it block my agent? Yes — that's the point. A REJECTED verdict is designed to send the agent back to fix findings instead of presenting broken work. Your standing rule decides how hard the stop is.
What about false positives? Verdicts come with specific findings and the math, so they're auditable in seconds — you're never asked to trust a bare score. The new secrets-in-logs check was measured on 34,849 real third-party source files before launch: it flagged 5 lines, all genuine password or credential logging.
initialize/tools/list are public, so clients and directories can introspect the server.30-day free trial, then USD $30/month (launch offer: 50% off for 3 months). Volume and academic pricing: [email protected].
Built by Verificate Pty Ltd (Sydney, Australia) — an IBM Business Partner. Verificate builds sovereign AI infrastructure: the HELIX inference engine (calibrated confidence scores on every answer), the deterministic Decision Transformer, and this MCP validation server. Product page: https://verificate.ai/mcp · Official registry: ai.verificate/mcp
This repo (the stdio bridge, client configs and CI examples) is MIT — use it freely. The Verificate validation engine and hosted gateway it talks to are a commercial service (30-day free trial, then subscription): the deterministic checks and the model review run server-side and are not part of this repository.
🌐 Not an English speaker? Install instructions in हिन्दी · Português · Bahasa Indonesia · Español · 中文 · Tiếng Việt → INSTALL.md
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add verificate --transport http https://mcp.verificate.ai/mcp{
"mcpServers": {
"verificate": {
"url": "https://mcp.verificate.ai/mcp",
"transport": "http"
}
}
}code --add-mcp '{"name":"verificate","url":"https://mcp.verificate.ai/mcp","transport":"http"}'Runs as a hosted service. Your client connects over the network and nothing is installed locally.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/verificate-mcp-quickstart to learn what the "Verificate Mcp Quickstart" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
claude mcp add --transport http verificate https://mcp.verificate.ai/mcp
claude mcp add --transport http verificatedocker run -i -e VERIFICATE_TOKEN=<your-token> verificate-mcp| Name | What it does |
|---|---|
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 res |
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. |
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 complete |
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 |
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 |
| Name | What it does |
|---|---|
gate_my_changes | Run the Verificate merge gate on code and loop until it is approved: validate, fix every finding, re-validate. |
review_my_plan | Gate an implementation plan before any code is written: validate it, address every finding, re-validate. |
start_unit | Write a one-page unit card (goal, unit, scope, acceptance checks, steps) instead of a plan document, then validate it once with validate_plan. |
triage_message | Classify a new user instruction as refine / queue / new goal before acting, so earlier instructions and the active unit are not lost. |
record_progress | File a progress record (commit, CI run, acceptance results, open commands) instead of a report, evidence file or handover. |
| Name | What it does |
|---|---|
What runs on every review | Each deterministic check, what it vetoes, the model review stage, and the checks not run on shared infrastructure. |
Example rejection verdict | A verbatim REJECTED 30.8/100 verdict from the production gateway. |
Track record (benchmark + dogfood proof) | Measured proof: the November 2026 frozen A/B (6 unsafe approvals in 36 -> 0), the September 0/6-vs-6/6 benchmark, our own engineering use, and the knowledge base it guards. |
Unit card template | One-page plan replacement: goal, unit, scope, acceptance checks, at most 3 risks, steps mapped to checks. |
Progress record template | Replaces status reports, evidence files and handovers: commit, CI run, acceptance results, open commands. |
Instruction triage template | Classify a new user instruction (refine / queue / new goal) instead of re-planning. |
Read live from the server on November 15, 2026.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/verificate-mcp-quickstart)Nothing comparable is listed yet.
v1.8.7v1.8.7 — works with no key: tokenless calls hit the free tierRelease notesv1.8.6v1.8.6 — bridge parity: enriched tools, prompts and resources served locallyRelease notesv1.8.5v1.8.5 — permanent endpoint, full capability surface, enriched tool definitionsRelease notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "verificate-mcp-quickstart" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.