Schema | Houtini LM

Houtini LM

Describes the environment variables required to run the server.

Name	Required	Description
`HOUTINI_LM_MODEL`	No	Pin a specific model to use, e.g. gpt-5.2. Useful when the endpoint lists many models that all score the same in routing.
`HOUTINI_LM_API_KEY`	No	API key for the endpoint, if it requires one.
`HOUTINI_LM_THINKING`	No	Controls model thinking: 'auto' (default) switches thinking off for models detected as supporting the toggle, 'off' forces it off for every call, 'on' forces thinking on.
`HOUTINI_LM_SERIALISE`	No	Set to 0 to turn off queuing of calls one at a time (default queues calls serially, which suits a single GPU). OpenRouter skips the queue; batching backends like vLLM and OpenAI can disable it.
`HOUTINI_LM_MIN_TOKENS`	No	Minimum output token floor, default 4096 (caps below this passed by MCP clients are ignored). Set to 0 to disable the floor.
`HOUTINI_LM_STRUCTURED`	No	Set to 1 so each inference result also carries a structuredContent block (answer, model, tokens, timing, quality flags) to read as JSON. Leave off for Claude Code.
`HOUTINI_LM_ENDPOINT_URL`	No	The URL of the OpenAI-compatible endpoint to delegate to, e.g. an LM Studio, Ollama, vLLM, SGLang, LiteLLM router, OpenRouter or cloud API endpoint (default is http://localhost:1234).

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityMaintained

ResponsivenessResponsive