Schema | mcp-llama-swap

mcp-llama-swap

Describes the environment variables required to run the server.

Name	Required	Description	Default
`LLAMA_SWAP_CONFIG`	No	Path to configuration JSON file. Overrides default config path.

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
list_modelsA	List available llama.cpp model configurations and their load status.
get_current_modelA	Get the currently loaded llama.cpp model.
swap_modelA	Swap to a different llama.cpp model. Unloads any currently loaded model, loads the requested one, and waits for the health endpoint to confirm readiness. Args: model: Alias of the model to load
create_model_configA	Generate a new service config for a llama-server model. Creates a launchd plist (macOS) or systemd unit (Linux) that can be used with swap_model. Args: name: Short alias for the model (e.g., "coder", "planner") model_path: Absolute path to the GGUF model file context_size: Context window size (default: 4096) gpu_layers: Number of GPU layers, -1 for all (default: -1) port: Port for llama-server (default: 8000)

Interactive templates invoked by user choice

Name	Description
`swap-workflow`	Guided workflow for planning with a reasoning model, then implementing with a coding model.

Contextual data attached and managed by the client

Name	Description
`config_resource`	Current llama-swap configuration.
`status_resource`	Current model status and health.

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/oussama-kh/mcp-llama-swap'

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