MCPLow riskUnclaimed

keygrant

Run commands with API keys injected per call — values never enter model context.

bazingaedwardbazingaedward/keygrantUpdated Oct 9, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.bazingaedward/keygrant",
  "description": "Run commands with API keys injected per call — values never enter model context.",
  "title": "keygrant",
  "repository": {
    "url": "https://github.com/bazingaedward/keygrant",
    "source": "github"
  },
  "version": "0.1.3",
  "websiteUrl": "https://keygrant.app",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "keygrant",
      "version": "0.1.3",
      "runtimeHint": "uvx",
      "transport": {
        "type": "stdio"
      },
      "packageArguments": [
        {
          "value": "mcp",
          "type": "positional"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—python
Installs—pypi:keygrant@0.1.3
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. #20.1.3latestOct 9, 2026
  2. #10.1.2Oct 8, 2026