Mmcp.market

Gnt MCP server

by gnt-ai·io.github.gnt-ai/gnt·v0.6.0

Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.

A85/100grade A
What users say
No reviews yet
Be the first
Safety scan
A85/100

full report

Adoption
Growing

30 stars

Reviews

Write one

Nobody has reviewed Gnt yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Gnt tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 178ms (auth required)20/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityauth enforced (unknown)9/15
  • Maintenancelast push 6 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Gnt repository's README, as published. We do not edit it. Read it on GitHub

Run the setup below once and every agent your team runs has a git-native rulebook it has to check over MCP before it acts, approved the same way your code already is: a merged pull request.

  • Rules live in your repo as files and ship through normal PRs, not a dashboard click.
  • Agents call check_action over MCP before anything risky (a refund, a delete, a message to a customer) and get back an allow/block/escalate verdict.
  • Every rule traces back to the git file and the PR that approved it, so "why did the agent do that" always has a paper trail.

Prefer not to run any of this yourself? The hosted version at gntai.dev does the same thing without you standing up a Postgres instance.

Get started (30 seconds)

npm install -g @gnt-ai/cli
gnt login
gnt connect github
gnt prebrain
# merge the opened PR on GitHub. that merge is the approval

Try it with Docker first

To see a real check_action response before installing Node or npm, clone the repository and run the Docker-only demo:

./demo.sh

It builds the full local stack in an isolated gnt-demo Compose project, seeds an approved refund rule, calls checkaction, and prints a curl command you can run again. Without an Anthropic key the real fail-closed path returns needshuman; pass GNTDEMOANTHROPICAPIKEY=sk-ant-... ./demo.sh to opt in to the model's grounded policy verdict. The demo uses deterministic local embeddings and throwaway localhost-only secrets, so it does not need a ZeroEntropy key.

Nothing for gnt prebrain to scan yet? Run gnt init first — it scaffolds rules/ locally

with a couple of example rule files so there's something real to look at and edit, and points

you at gnt prebrain --starter-packs for a curated pack to start from instead.

That merge lands a rule file in your connected repo, shaped like this:

your-repo/
└── rules/
    ├── refund-approval-threshold.md
    └── contract-legal-cc.md

Each file is plain markdown with YAML frontmatter:

---
title: Never refund over $500 without a manager
status: approved
confidence: 0.91
owner_id: finance-team
source_citations: [...]
source: slack
tags: [refunds, finance]
last_validated_at: 2026-07-20
version: 1
superseded_by: null
approved_by: jane@company.com
approved_at: 2026-07-21T14:03:00Z
created_at: 2026-07-18T09:12:00Z
pr_number: 142
pr_url: https://github.com/your-org/your-repo/pull/142
---

Refunds over $500 need manager sign-off before they go out...

See it in action

There's no captured transcript to show yet (see the gap noted at the bottom of this README). Here's the actual response shape a check_action call returns, straight from the tool's contract:

{
  "verdict": "blocked",
  "reason": "Refund exceeds the $500 threshold without manager sign-off (rules/refund-approval-threshold.md)",
  "cited_rules": [
    { "id": "refund-approval-threshold", "title": "Never refund over $500 without a manager" }
  ],
  "rules_retrieved": 3
}

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

claude mcp add --transport http gnt https://api.gntai.dev/mcp
Add to Cursor

Gnt: common questions

Is Gnt MCP server safe?
Yes, by our scan: it is graded A (85/100). Read the Gnt safety report
How do I install Gnt?
It runs remotely at api.gntai.dev. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Gnt need an API key?
Yes. The endpoint refuses requests without credentials; the publisher's docs say how to get them.
Is Gnt maintained?
The last commit was 6 days ago (2026-09-18). The latest release is v0.6.0.
Is Gnt up?
100% of our last 21 checks got an answer. We check remote servers about four times a day.
What can I use instead of Gnt?
Servers from other publishers that do the same job: argot MCP server, Prumo MCP server and Git MCP server. Compare all Gnt alternatives.

Alternatives to Gnt

Same job from other publishers: the closest match first, then the best rated.

All Gnt alternatives →
  • argot
    Read-only context and complete checks against patterns learned from git history. Local; no LLM.
    B
  • Prumo
    Checks the context files a coding agent reads against the git index, and reports what drifted.
    A
  • Git
    Comprehensive Git MCP server enabling native git tools including clone, commit, worktree, & more.
    A
  • Contentrain
    Git-native content governance for AI agents — 27 deterministic MCP tools over stdio and HTTP.
    A
  • Agent Memory
    Git-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.
    A

More from gnt-ai →