$ loading_
Manage local model runtimes with unified discovery, checks, lifecycle control, and inference.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Local AI MCP" yet — see the docs or source repo.
Scan local model runtimes on this machine, such as Ollama and LM Studio, then list available models, providers, versions, ports, and current status grouped by runtime.
A structured inventory of local runtimes and models, including status, source, and connection details.
Evaluate whether this device can run a local model at the Llama 3 class, using CPU, RAM, VRAM, and available backends to provide compatibility, risks, and recommended settings.
A hardware compatibility analysis explaining feasibility, bottlenecks, and recommended model or configuration options.
Use an available local model runtime to run inference: summarize the following meeting notes and report which runtime and model were used. If the preferred provider is unavailable, automatically fall back to another available provider.
The inference result plus metadata on the runtime, model used, and any fallback that occurred.
Connect local Ollama to MCP apps for chat, model management, and generation.
Manage LM Studio models via MCP for loading, unloading, and configuration.
Lets AI assistants manage LLM inference, backends, and VRAM via MCP.
Delegate summarization, classification, extraction, and drafting tasks to a local LLM.
Delegate low-risk tasks to a cheaper model with main-agent review.
Build, debug, and manage software tasks with natural language across LLMs.