Manage Ollama operations: check server status, list and pull models, generate text, get hardware info, document code, analyze quality, and summarize context.
MIT
396,342 tools. Last updated 2026-08-05 10:47
"ollama" matching MCP tools:
- List, pull, or delete models on an existing Ollama server by specifying the VM IP address and action.MIT
- Check if the Ollama daemon is reachable and view currently running models. Use this as the first step to confirm service health before using other tools.MIT
- List all locally installed Ollama models with names, sizes, and modification dates.AGPL 3.0
- Monitor Ollama server status and diagnose issues to ensure reliable local LLM operations.MIT
- Downloads a model from the Ollama registry, making it available for local execution.AGPL 3.0
Matching MCP Servers
- AlicenseAqualityCmaintenanceHardened MCP bridge to the full Ollama ecosystem — local and cloud models. 6 tools covering health, model management, chat, and generation with SSRF mitigation, singleton HTTP client, and structured error handling. Two deps, one file.Last updated63MIT
- AlicenseAqualityBmaintenanceOffloads cheap work from cloud LLM agents to a local Ollama model, reducing costs and keeping frontier models focused on complex tasks.Last updated82MIT
- Retrieve all downloaded Ollama models available for use through the MCP Ollama Server integration.MIT
- Lists configured model runtime providers with their host, live detection status, and capabilities. Optionally filter to a single provider.Creative Commons Attribution Non Commercial No Derivatives 4.0 International
- Search a curated catalog of local models by name, family, or task to find models matching your criteria.Creative Commons Attribution Non Commercial No Derivatives 4.0 International
- List local Ollama models and retrieve queryable paid route labels for accessing AI models with payment options.MIT
- Optimize LLM inference by scanning GPU details, benchmarking memory bandwidth, and checking ML runtimes and environment variables.Apache 2.0
- List free-seat status and requestable local runtimes such as Ollama, llama.cpp, LM Studio, OpenAI-compatible servers, and vLLM.MIT
- List all installed Ollama models on your local machine and check their memory load status to discover available model names for chat, generation, or model info queries.MIT
- Send multi-turn chat requests to an Ollama model for conversational interactions with history, such as follow-ups or multi-step reasoning. Preserves context across messages.MIT
- Inspect detailed metadata of an installed Ollama model including architecture, license, and parameters before using it for chat or generation. Read-only and idempotent.MIT
- Send a prompt to a local Ollama model for immediate private answers. Use it for summarising text, drafting boilerplate, or extracting fields without sending data off-machine.MIT
- Generate single-turn text completions from Ollama models for code, summarization, translation, and other one-shot tasks without conversation history.MIT
- Install Ollama directly on macOS without Homebrew or sudo, enabling local inference for massive context processing. Supports downloading, starting the service, and pulling models like gemma3:12b for headless setups.MIT
- Check if the Ollama server is reachable and retrieve its version. Use this health check as a precondition before other tools.MIT
- Pull a model from the Ollama library to your local machine when not already installed. Use after checking available models, before running chat or generation.MIT