lookupd

io.github.mdfifty50-boop/agent-guard

not probeable (local package)

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided description

Constitutional guardrails and loop detection for AI agents

Summary by lookupd

Lets an agent check its own actions against configured policy rules and detect repeated tool-call loops before running them.

Install

Claude Code, npm package (stdio)

claude mcp add agent-guard -- npx -y agent-guard-mcp

Codex, npm package (stdio)

codex mcp add agent-guard -- npx -y agent-guard-mcp

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

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

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

Details

Badge for your README

Shows this live status and links here; updates hourly.

lookupd status badge for io.github.mdfifty50-boop/agent-guard

[![lookupd status](https://lookupd.com/badge/io.github.mdfifty50-boop/agent-guard.svg)](https://lookupd.com/servers/io.github.mdfifty50-boop/agent-guard)