io.github.jyswee/a2a-trustgate

up checked 2026-11-11T06:38:05.659Z

Unclaimed · Unverified

Publisher-provided description

A2A TrustGate: 4-gate firewall that screens every AI-agent action before it runs. 50 tools.

Summary by lookupd

Screens AI agent actions through a four-gate safety firewall before they run, and can issue a tenant API key for access.

Install

Claude Code, remote (sse)

claude mcp add --transport sse a2a-trustgate https://mcp.a2ainfrastructure.com/sse

Claude Code, npm package (stdio)

claude mcp add a2a-trustgate -- npx -y a2a-trustgate

Codex, remote (sse)

codex mcp add a2a-trustgate --url https://mcp.a2ainfrastructure.com/sse

Codex, npm package (stdio)

codex mcp add a2a-trustgate -- npx -y a2a-trustgate

Cursor, remote (sse) → .cursor/mcp.json

{
  "mcpServers": {
    "a2a-trustgate": {
      "type": "sse",
      "url": "https://mcp.a2ainfrastructure.com/sse"
    }
  }
}

Cursor, npm package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "a2a-trustgate": {
      "command": "npx",
      "args": [
        "-y",
        "a2a-trustgate"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

a2a_get_started Explains what A2A TrustGate is and how to activate this MCP server (no API key on this session yet).
a2a_signup Create a new A2A TrustGate tenant and get an API key (shown once), unlocking all safety tools in this session immediately. Agent-first: only a short tenant slug

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.jyswee/a2a-trustgate.svg)](https://lookupd.com/servers/io.github.jyswee/a2a-trustgate)