gnt MCP Server
OfficialConnects a GitHub repository for rule storage and approval via pull requests.
Integrates with Intercom for customer communication rule management.
Integrates with Linear for issue tracking rule management.
Integrates with Notion for knowledge base rule management.
Connects a Slack workspace for rule review and notifications.
Integrates with Zendesk for customer support rule management.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@gnt MCP Serverwhat rules apply to refunds over $500?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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_actionover 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.

gnt prebrain scanning a repo, opening a PR, and getting it merged. A real terminal session, not a mockup.
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 approvalThat merge lands a rule file in your connected repo, shaped like this:
your-repo/
└── rules/
├── refund-approval-threshold.md
└── contract-legal-cc.mdEach 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...Related MCP server: PolicyGuard
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
}verdict is one of allowed, blocked, or needs_human. needs_human is the fail-closed
default: no approved rule covers the action, retrieval failed, or the check couldn't complete.
It never guesses.
What it does
One MCP endpoint, five tools:
Tool | What it does |
| Checks a described action against your approved rules before an agent takes it. Returns |
| Semantic search over your org's approved rules, optionally filtered by tag. An empty list means no approved rule covers the query. |
| Fetches one approved rule by id, with its provenance (who approved it, when, what it was cited from). |
| Lists every compiled skill pack version for your org, newest first. |
| Fetches a compiled skill pack's manifest and file list by id. |
Prerequisites
Requirement | Check | Get it |
Node >=22.13 |
|
Install
Method | Command |
curl |
|
npm |
|
gnt needs Node >=22.13. If the CLI fails to start with a version error, update Node first and confirm with
node --version.
Common commands
gnt login # sign in, store an API key locally
gnt connect github # connect the repo your rules PRs open against
gnt prebrain # scan sources, extract candidate rules, open PRs
gnt review # review rules awaiting approval
gnt status # show brain status
gnt pull # download the latest skill pack
gnt gaps # list uncovered queries with no approved ruleConfig
Variable | Default | What it controls |
|
| API endpoint the CLI and MCP calls hit |
|
| Web app used for |
|
| Where |
Privacy
No analytics or telemetry dependency in the CLI or the web app.
gnt prebrain's default extraction mode is cloud, not on-device: your source text goes straight to Anthropic's API (or Vercel AI Gateway with zero-data-retention, if you configure it), never to gnt's own servers. Fully on-device extraction needs--mode localagainst a local Ollama daemon.The extracted rule candidates still get sent to gnt's API to open the PR. Raw source text stays off gnt's servers in cloud mode; the resulting rule text doesn't.
Rules live in your connected GitHub repo and in gnt's own database. The MCP tools read from gnt's store, not by cloning your repo on every call.
Self-hosting:
apps/apionly sends error data to Sentry if you setSENTRY_DSNyourself. Leave it unset and nothing goes out.
Team setup
Who writes rules: anyone with access to your connected repo, either through
gnt prebrain(batch-extracted from real sources) orgnt review(hand-proposed).How approval works: merging the PR is the approval. There's no separate publish step.
What gets committed:
rules/<rule-id>.mdfiles with the frontmatter shown above and a plain markdown body.
Troubleshooting
Self-hosting:
gnt login's browser step needsapps/webrunning. The base self-host compose stack doesn't start it by default. Runapps/webseparately (its ownpnpm devor build) so/cli-loginhas somewhere to land, then retrygnt login.
ValueError: refusing to start: these settings still have their .env.example placeholder value...Achange-me-...string is still sitting inapps/api/.env. The error names every offending field; generate a real value for each and retry.
storefails to start withGNT_STORE_INTERNAL_API_SECRET is not set.apps/store/.envwasn't filled in, or wasn't picked up. Confirm the file exists at that exact path, not still named.env.example.
Every store-to-api call gets rejected with 401 or 403, even though both services are up.
STORE_INTERNAL_API_SECRET/APPROVAL_SIGNING_SECRETinapps/api/.envdon't byte-for-byte matchGNT_STORE_INTERNAL_API_SECRET/GNT_APPROVAL_SIGNING_SECRETinapps/store/.env. This fails closed by design. Regenerate both pairs so the two files agree.
A rule fails to save with an embedding or rerank error.
apps/store/.envis missingZEROENTROPY_API_KEY, or it's still empty. Get a real one from zeroentropy.dev.
Full command reference
gnt login
gnt logout
gnt connect <app> github, slack, notion-mcp, monday-mcp, linear-mcp, jira-mcp,
sentry-mcp, granola-mcp, zoom-mcp, figma, datadog,
gitlab-threads, hubspot, airtable, openclaw, hermes
gnt disconnect <app>
gnt status
gnt billing
gnt review
gnt pull
gnt gaps
gnt prebrain scan local sources, extract candidate rules, open batched draft
PRs (~60 flags for source paths and extraction mode, see
`gnt prebrain --help`; --mode cloud|local, cloud is the default)
gnt stale
gnt keys list|create|revoke|rotate
gnt webhook list|create|revoke
gnt org show|rename|invite|removeLearn more
Self-hosting walkthrough:
docs/self-hosting/README.mdProduction hardening after self-hosting:
apps/api/DEPLOY.mdSecurity policy:
SECURITY.md
License
Copyright © 2026 gnt.ai. Licensed under FSL-1.1-Apache-2.0, source-available today. See LICENSE for the terms and NOTICE for the trademark rule on forks: two years after this repo went public it converts to Apache-2.0 in full.
Contributing
See CONTRIBUTING.md for dev setup and how to open a PR. Every commit needs a Signed-off-by trailer (git commit -s), the Developer Certificate of Origin instead of a CLA. No separate form, just the flag.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceProvides AI agents with queryable, version-controlled project rules and coding standards. Enables validation, rule-based guidance, and task summaries to keep AI work aligned with your project's conventions without repeating context.Last updated2MIT
- FlicenseAqualityDmaintenanceProvides policy-based access control, incident tracking, and compliance monitoring to govern AI agent behavior. It enables organizations to enforce security rules and maintain audit trails by validating agent actions against trust levels and pattern-based policies.Last updated6
- Alicense-qualityCmaintenanceTransforms static coding standards into a queryable live data store for AI agents, delivering task-specific rules and fix guidance on demand. This optimizes context window usage through progressive disclosure, ensuring agents apply relevant governance without loading massive documentation.Last updated2MIT
- Alicense-qualityCmaintenanceCentralizes AI behavior rules and applies them across tools like Codex, Claude Code, and Cursor, enabling agents to fetch up-to-date rules before responding.Last updated1MIT
Related MCP Connectors
Deterministic compliance and vertical knowledge bases for autonomous agents. Free 24hr trial.
Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping.
AI reasoning checks any document against known international standards before your agent acts on it.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gnt-ai/gnt'
If you have feedback or need assistance with the MCP directory API, please join our Discord server