local-llm-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROQ_API_KEY | No | API key for Groq cloud backend. | |
| AGNES_API_KEY | No | API key for Agnes cloud backend. | |
| MINIMAX_API_KEY | No | API key for MiniMax cloud backend. | |
| OLLAMA_BASE_URL | No | Override base URL for Ollama backend. | |
| CEREBRAS_API_KEY | No | API key for Cerebras cloud backend. | |
| DEEPSEEK_API_KEY | No | API key for DeepSeek cloud backend. | |
| OPENROUTER_API_KEY | No | API key for OpenRouter cloud backend. | |
| LOCAL_LLM_MIN_FREE_GB | No | Minimum free RAM in GB before local calls are refused. | 16 |
| DEEPSEEK_DEFAULT_MODEL | No | Override default model for DeepSeek backend. |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_backendsA | List all built-in and custom backends, including key status and protocol. |
| refresh_backendsB | Reload custom_backends.json without restarting the MCP server. |
| set_backendA | Create, update, or remove a custom backend in custom_backends.json. Args: name: Backend id, e.g. my_local_qwen. Lowercase letters, numbers, _ or -. base_url: OpenAI-compatible or Anthropic-compatible base URL. default_model: Model id. Empty means auto-resolve from /models where possible. local: 1 for local RAM-guarded backend, 0 for cloud backend. api_key_env: Optional environment variable name for the API key. protocol: openai or anthropic. remove: 1 removes the custom backend. |
| local_statusA | Report memory, guard config, backend reachability, and config file paths. |
| set_guardC | Change safety guard settings live and persist them to config.json. |
| set_system_prefixA | Set or clear a fixed system prefix prepended to every ask_local_model call. |
| list_local_modelsB | List model ids on a backend. Works when the backend exposes GET /models. |
| list_modelsD | Alias for list_local_models. |
| ask_local_modelA | Send a prompt to a backend model and return text plus metadata. Delegated models cannot read or edit files by themselves. They only return text to the main agent, which remains responsible for validation, edits, and tests. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools target distinct aspects (querying, listing, configuration, status). The alias list_models for list_local_models is redundant but clearly documented, causing minor potential confusion.
Tools consistently follow verb_noun pattern with underscores (e.g., ask_local_model, list_backends, set_backend). The sole exception local_status is descriptive and fits the pattern.
9 tools cover the core operations for managing local LLM backends, guards, and queries without being excessive or insufficient.
The tool set covers CRUD for backends, querying, and configuration. A minor gap is the lack of a dedicated tool for detailed backend info, but list_backends provides status.