Gnt is answering right now. Last checked 15 min ago. Last commit 22 Oct 2026.
Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.
What the code does
We read the source, 1 d ago · rules 995398eba69f
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
curl --proto '=https' --tlsv1.2 -LsSf https://astral.sh/uv/install.sh | sh
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Gnt missed one check this week
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 15 min ago.
claude mcp add gnt --transport http https://api.gntai.dev/mcphttps://api.gntai.dev/mcp[mcp_servers.gnt]
url = "https://api.gntai.dev/mcp"{
"mcpServers": {
"gnt": {
"url": "https://api.gntai.dev/mcp"
}
}
}{
"servers": {
"gnt": {
"type": "http",
"url": "https://api.gntai.dev/mcp"
}
}
}This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.gntai.dev/mcp | streamable-http | needs auth | 574 ms | 15 min ago |
Alternatives to Gnt
same job, measured the same wayPre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
Approval gate and audit trail for AI agent actions: policy check first, proof after. Any MCP client.
Check user intent and proposed actions against approved semantic policies.
Agent-native CLI: provenance, cost governance, and execution contracts for AI agents.
Database guardrails for AI agents: check SQL against your Vericto rules before it runs.
Polymarket prediction-market intelligence + AI, GitHub & narrative feeds for agents, via x402.
Universal governance layer for AI agents. MCP-native, fail-closed, audit proofs and rollback.
Fact-check claims against live web sources: verdict, consensus, cited sources, PII redaction.
Gnt — questions
Answers built from our own checks of this server.