Back to code-only MCP servers

houtini-lm

active

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.

Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.

Get it

Repository
github.com/houtini-ai/houtini-lm
Package
npm: @houtini/lm
Run (stdio)
npx -y @houtini/lm
The usual command for this package registry; check the repository README for required settings.
License
Apache-2.0
Last update
2026-11-07
GitHub stars
★ 122
Homepage
houtini.com/how-to-cut-your-claude-code-bill-with-houtini-lm/

Listed in

Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.