MCPLow riskUnclaimed
gnt
Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.
gnt-aignt-ai/gnt
server.json
{
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"name": "io.github.gnt-ai/gnt",
"description": "Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.",
"repository": {
"url": "https://github.com/gnt-ai/gnt",
"source": "github"
},
"version": "0.6.0",
"websiteUrl": "https://gntai.dev",
"remotes": [
{
"type": "streamable-http",
"url": "https://api.gntai.dev/mcp"
}
]
}Permissions
DeclaredDetected
Runs code—None
Installs—None
Runs install scripts—None
Network
api.gntai.devapi.gntai.devNeeds credentialsNoneNone
Outside the workspace—None
Agent tools—None
Checks
Low risk · Nothing worth a warning was found.
Not reviewed by a person · Checked by rules; the model review is not switched on yet.
Versions
- #10.6.0latestOct 7, 2026