Houtini Lm
未申請MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
インストール
claude mcp add houtini-lm -- npx -y @houtini/lm未申請リスティング
このMCPサーバーはあなたのものですか？
このリスティングは公開情報から自動的にインデックスされました。申請することで、ページの編集、互換性の設定、成長ツールのアンロックができます。2分以内に完了します。
このサーバーを申請するツール（21個）
chat
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.
code
yes
code_task
Built for code analysis. Pre-configured system prompt with temperature and output constraints tuned per model family via the routing layer.
code_task_files
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
context
no
custom_prompt
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
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
embed
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.
input
yes
instruction
yes
json_schema
no
language
no
list_models
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.
max_tokens
no
message
yes
model
no
paths
yes
stats
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.
system
no
task
yes
temperature
no