List the configured model runtime providers (Ollama, LM Studio, llama.cpp, optional OpenAI-compat / Moonshot) with their host, whether they are detected/live, and their capabilities. Optionally filter to a single provider.

List models installed/available on each detected provider. Without a provider arg, aggregates across all detected providers keyed by provider.

List models currently loaded into memory on each detected provider. Without a provider arg, aggregates across all detected providers keyed by provider.

Show detailed metadata for a specific model (family, parameter size, quantization, context length). Without a provider arg, queries all detected providers.

HEAVY: Download/pull a model onto a provider. WARNING: this may download multiple gigabytes and can take a long time. Without a provider arg, attempts the pull on every detected provider.

DESTRUCTIVE: Permanently delete a model from a provider. Requires confirm:true; without it the action is refused. The provider argument is REQUIRED so a delete cannot fan out across every detected runtime.

Load a model into memory so it is ready for inference. Optionally set keepAlive (e.g. '5m', '1h'). Without a provider arg, loads on every detected provider.

Unload a model from memory to free VRAM/RAM. Without a provider arg, unloads from every detected provider.

Check whether each provider's local runtime is reachable and report its version. Without a provider arg, checks all configured providers.

Report local hardware resources: platform, total/free RAM, CPU count, and detected GPUs with VRAM. Used to reason about which models can run locally.

Determine whether a model fits on the local hardware. Resolves the model weight size from the provider or the static catalog (or an explicit sizeBytes), estimates KV-cache overhead for a context length (default 4096), then compares weight+KV against free GPU VRAM, falling back to system RAM. Returns fits, target (gpu/cpu/none), weight/kv/required/available bytes.

HEAVY: Runs REAL inference. Executes one small completion against a loaded/loadable model and measures latency (ms) and throughput (tokens/sec). This consumes compute and may load the model. Without a provider arg, runs on the first detected provider.

Search the built-in catalog of well-known local models by name, family, or task. Note: this searches a curated static catalog, not the full live Ollama library (https://ollama.com/library).

Recommend local models for a task (chat/code/embed/vision/reasoning/general), ranked by task match and then by whether they fit the detected free GPU VRAM or system RAM. Returns a ranked list with fit flags.

DELEGATED INFERENCE: Offload a text/chat completion to a local model runtime for cost savings and privacy (data never leaves the machine). This is NOT a chat feature for the user; it delegates work to a local LLM. Provide either prompt or messages. Streams tokens via MCP progress notifications when the client supplies a progressToken (stream defaults to true). Without a provider arg, uses the first detected provider.

DELEGATED EMBEDDINGS: Offload embedding generation to a local model runtime for cost savings and privacy. Accepts a single string or an array of texts. Without a provider arg, uses the first detected provider.