Skip to content
Verified official

Local LLM Guard for Ollama / llama.cpp MCP

v0.14.1 changelog · 3

io.github.aiops-tools/ai-guardian

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

transport:stdio runtime:pypi

Target client

run in your project directory

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

setup guides: Claude Code Claude Desktop Cursor VS Code Zed Windsurf Cline Gemini CLI Grok LangChain

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

This listing does not declare its tools. Connect the server and your client will discover them on the handshake.