Houtini LM
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOUTINI_LM_MODEL | No | Pins the model to use. Useful when the server lists many models and automatic routing would otherwise pick the first listed. | |
| HOUTINI_LM_API_KEY | No | API key for the endpoint, if the endpoint requires one. | |
| HOUTINI_LM_THINKING | No | Controls model thinking: 'auto' (default), 'off', or 'on'. Auto disables thinking for models detected as supporting the toggle, off forces thinking off, on forces thinking on. | |
| HOUTINI_LM_SERIALISE | No | Controls request serialisation. Calls are queued one at a time by default; set to 0 to disable serialisation for OpenAI, a router, or batching backends like vLLM. | |
| HOUTINI_LM_MIN_TOKENS | No | Minimum output token floor. Defaults to 4096, so smaller max_tokens values passed by MCP clients are ignored unless set to 0. | |
| HOUTINI_LM_STRUCTURED | No | When set to 1, each inference result also includes a structuredContent block with the answer, model, tokens, timing and quality flags as JSON. Leave off for Claude Code. | |
| HOUTINI_LM_ENDPOINT_URL | No | The URL of the OpenAI-compatible endpoint (e.g. LM Studio, Ollama, vLLM, LiteLLM, OpenAI, OpenRouter). Defaults to the local LM Studio endpoint at http://localhost:1234. |
Instructions
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.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessResponsive