Loomal

Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.

0 starspypi: mcp-agenttrust

About AgentTrust

AgentTrust is an MCP (Model Context Protocol) server published by assister-xyz in the official MCP registry, listed under Autonomous Agents on Loomal. Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.

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

Development happens in the open at github.com/assister-xyz/quality-oracle.

Use AgentTrust with your agent

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

Frequently asked questions

What is AgentTrust?
AgentTrust is an MCP (Model Context Protocol) server by assister-xyz in the Autonomous Agents category. Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
How do I connect AgentTrust to Claude, Cursor, or another MCP client?
Install AgentTrust from its pypi package (mcp-agenttrust) 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 AgentTrust open source?
Yes — the source code is public at github.com/assister-xyz/quality-oracle.
Can AI agents pay to use AgentTrust?
Not yet through Loomal — AgentTrust 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 AgentTrust? Claim this listing free by verifying GitHub ownership, or contact us.