MCPLow riskUnclaimed

Nogra

Verify-before-done trust layer for AI-assisted work. 32 tools, local-first, no credentials.

nograainograai/nogra-mcpUpdated Jul 6, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.nograai/nogra-mcp",
  "description": "Verify-before-done trust layer for AI-assisted work. 32 tools, local-first, no credentials.",
  "title": "Nogra",
  "repository": {
    "url": "https://github.com/nograai/nogra-mcp",
    "source": "github"
  },
  "version": "1.0.3",
  "websiteUrl": "https://nogra.ai",
  "packages": [
    {
      "registryType": "npm",
      "registryBaseUrl": "https://registry.npmjs.org",
      "identifier": "@nograai/mcp",
      "version": "1.0.3",
      "runtimeHint": "npx",
      "transport": {
        "type": "stdio"
      }
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:@nograai/mcp@1.0.3
Runs install scripts—None
NetworkNoneNone
Needs 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

  1. #11.0.3latestOct 7, 2026