Skip to main content
Glama
HenryLinyy

local-llm-mcp

by HenryLinyy
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GROQ_API_KEYNoAPI key for Groq cloud backend.
AGNES_API_KEYNoAPI key for Agnes cloud backend.
MINIMAX_API_KEYNoAPI key for MiniMax cloud backend.
OLLAMA_BASE_URLNoOverride base URL for Ollama backend.
CEREBRAS_API_KEYNoAPI key for Cerebras cloud backend.
DEEPSEEK_API_KEYNoAPI key for DeepSeek cloud backend.
OPENROUTER_API_KEYNoAPI key for OpenRouter cloud backend.
LOCAL_LLM_MIN_FREE_GBNoMinimum free RAM in GB before local calls are refused.16
DEEPSEEK_DEFAULT_MODELNoOverride default model for DeepSeek backend.

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
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

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/HenryLinyy/local-llm-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server