io.github.AIops-tools/ai-guardian

not probeable (local package)

Unclaimed · Unverified

Publisher-provided title

Local LLM Guard for Ollama / llama.cpp

Publisher-provided description

Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

Summary by lookupd

Lets agents scan prompts, enforce model policies, and capture and inspect traffic to local Ollama or llama.cpp LLM servers.

Install

Claude Code, pypi package (stdio)

claude mcp add ai-guardian -- uvx ai-guardian-aiops

Codex, pypi package (stdio)

codex mcp add ai-guardian -- uvx ai-guardian-aiops

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

{
  "mcpServers": {
    "ai-guardian": {
      "command": "uvx",
      "args": [
        "ai-guardian-aiops"
      ]
    }
  }
}

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

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.AIops-tools/ai-guardian.svg)](https://lookupd.com/servers/io.github.AIops-tools/ai-guardian)