Loomal

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

3 starspypi: haldir

About Haldir

Haldir is an MCP (Model Context Protocol) server published by exposureguard in the official MCP registry, listed under Autonomous Agents on Loomal. Guardian layer for AI agents: identity, secrets, audit via MCP.

It ships as a Python package on PyPI (haldir), so any MCP client that can launch a local process can run it.

Development happens in the open at github.com/exposureguard/haldir, where the project has earned 3 GitHub stars.

Use Haldir with your agent

Claude Code · one command
claude mcp add haldir -- uvx haldir
Claude Desktop, Cursor & other MCP clients · config
{
  "mcpServers": {
    "haldir": {
      "command": "uvx",
      "args": [
        "haldir"
      ]
    }
  }
}
pypihaldir

Frequently asked questions

What is Haldir?
Haldir is an MCP (Model Context Protocol) server by exposureguard in the Autonomous Agents category. Guardian layer for AI agents: identity, secrets, audit via MCP.
How do I connect Haldir to Claude, Cursor, or another MCP client?
Install Haldir from its pypi package (haldir) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.
Is Haldir open source?
Yes — the source code is public at github.com/exposureguard/haldir, with 3 GitHub stars.
Can AI agents pay to use Haldir?
Not yet through Loomal — Haldir is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.

Listing data from the official MCP registry and GitHub, refreshed periodically. Not affiliated with the maintainer unless claimed. Maintain Haldir? Claim this listing free by verifying GitHub ownership, or contact us.