mcpcost

io.github.AIops-tools/ai-guardian

Local LLM Guard for Ollama / llama.cpp

Is the Local LLM Guard for Ollama / llama.cpp MCP server down? Yes. It has given no valid answer since 2026-10-17: crashed on start.

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

crashed on start down since 2026-10-17 · probed 2026-11-14 · unchanged since 2026-11-08

MCP error -32000: Connection closed
Run it
uvx ai-guardian-aiops@0.14.1 (stdio, probed in a container with the network off)
Host
pypi.org
Repository
https://github.com/AIops-tools/AI-Guardian
Registry
active, updated 2026-11-08 · registry entry

Compare this server with others.

More servers

Other registry entries on pypi.org, the ones next to this name; all of them.

Servers that mention guardian.

Badge for the README

mcpcost: crashed on start

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Atom feed

A mail when this server changes

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.

For the publisher