AgentAvow Trust

Overview

AgentAvow Trust is a Model Context Protocol (MCP) server: Signed, offline-verifiable safety scores for the MCP servers, packages & tools an agent connects to. In practice that means any MCP-compatible AI assistant can call AgentAvow Trust's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Python package agentavow-trust (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.4.2.

AgentAvow Trust is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain AgentAvow Trust for agentavow.com, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "agentavow_trust": {
      "command": "uvx",
      "args": [
        "agentavow-trust"
      ]
    }
  }
}