MCPLow riskUnclaimed

Haldir

Guardian layer for AI agents: identity, secrets, audit via MCP.

ExposureGuardexposureguard/haldir★ 4Updated Apr 5, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.ExposureGuard/haldir",
  "description": "Guardian layer for AI agents: identity, secrets, audit via MCP.",
  "title": "Haldir",
  "repository": {
    "url": "https://github.com/ExposureGuard/haldir",
    "source": "github"
  },
  "version": "0.1.0",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "haldir",
      "version": "0.1.0",
      "transport": {
        "type": "stdio"
      }
    }
  ]
}

Permissions

DeclaredDetected
Runs code—python
Installs—pypi:haldir@0.1.0
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. #10.1.0latestOct 7, 2026