TrustAgent — counterparty verification MCP Server

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

claude mcp add trustagent-mcp -- npx -y trustagent-mcp

{
  "mcpServers": {
    "trustagent-mcp": {
      "args": [
        "-y",
        "trustagent-mcp"
      ],
      "command": "npx"
    }
  }
}

[mcp_servers.trustagent-mcp]
command = "npx"
args = ["-y", "trustagent-mcp"]

{
  "mcpServers": {
    "trustagent-mcp": {
      "args": [
        "-y",
        "trustagent-mcp"
      ],
      "command": "npx"
    }
  }
}

{
  "mcpServers": {
    "trustagent-mcp": {
      "args": [
        "-y",
        "trustagent-mcp"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: TRUSTAGENT_URL (Service to query. Defaults to the hosted deployment.), TRUSTAGENT_WALLET_KEY (Private key of a funded Base wallet. Enables the four paid tools, which settle per call in USDC over x402. Omit to run the free tools only — they need no wallet. Requires the optional peer dependency x402-fetch.), TRUSTAGENT_MAX_PER_CALL_USD (Refuse any single paid call above this amount.), TRUSTAGENT_MAX_SESSION_USD (Total spend ceiling across all paid calls in one session. A model looping on a retry is the realistic failure, and a per-call limit does not catch it.). The author declared them in the registry entry; get the values from the project itself.