discover
Health check and speed readout. Returns model name, context window, capability profile, connection latency (labelled explicitly — this is the /v1/models fetch round-trip, not inference speed), and the active model's measured tok/s and TTFT averaged over the session. Before any real call has run, mea
How to use it
discover is exposed by the Houtini Lm MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the discover tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Houtini Lm
claude mcp add houtini-lm -- npx -y @houtini/lmOther tools in Houtini Lm (20)
The workhorse. Send a task, get an answer. The description includes planning triggers that nudge Claude to identify offloadable work when it's starting a big task.
yes
Built for code analysis. Pre-configured system prompt with temperature and output constraints tuned per model family via the routing layer.
Like codetask, but the local LLM reads files directly from disk — source never passes through the MCP client's context window. Use this when reviewing multiple related files, or a single large file that's awkward to paste. Files are read in parallel with Promise.allSettled, so one unreadable file do
no
Three-part prompt: system, context, instruction. Keeping them separate prevents context bleed - consistently outperforms stuffing everything into one message, especially with local models. I tested this properly one weekend - took the same batch of review tasks and ran them both ways. Splitting thin
Generate text embeddings via the OpenAI-compatible /v1/embeddings endpoint. Requires an embedding model to be available - Nomic Embed is a solid choice. Returns the vector, dimension count, and usage stats.
yes
yes
no
no
Lists everything on the LLM server - loaded and downloaded - with full metadata: architecture, quantisation, context window, capabilities, and HuggingFace enrichment data. Shows capability profiles describing what each model is best at, so Claude can make informed delegation decisions.
no
yes
no
yes
Compact markdown dump of your offload stats — session and lifetime totals, per-model performance history, reasoning-token overhead — without the model catalog that discover prints. Cheap to call repeatedly to watch the 💰 counter climb.
no
yes
no