Manage Ollama operations: check server status, list and pull models, generate text, get hardware info, document code, analyze quality, and summarize context.
MIT
202,249 tools. Last updated 2026-06-14 11:06
"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
- Check if the Ollama server is reachable and retrieve its version. Use this health check as a precondition before 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
Matching MCP Servers
- AlicenseAqualityAmaintenanceHardened 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 updated62MIT
- Alicense-qualityAmaintenanceMCP server wrapping local Ollama models for offload from API-priced orchestrators. Nine stdio tools - generation, summarisation, analysis, drafting, code tasks (docstring/test/explain/review/types/refactor-suggest), diff-driven tasks (commit-message/pr-description/changelog/summary/impact), mechanical transforms, and model management (list/pull). Apache-2.0.Last updated28Apache 2.0
- Downloads a model from the Ollama registry, making it available for local execution.AGPL 3.0
- Retrieve all downloaded Ollama models available for use through the MCP Ollama Server integration.MIT
- Search the web using a tiered cascade of Brave, DuckDuckGo, and a scraper. Optionally summarize results or fetch the top result's content.MIT
- Fetch any URL, convert its content to markdown format, with built-in SSRF protection and caching. Optionally summarize the retrieved content using a local LLM.MIT
- Retrieve relevant passages from your personal knowledge base and generate answers using a local LLM, keeping your data private.MIT
- Extract entities, topics, key phrases, and summaries from text using configurable AI providers with automatic fallback.MIT
- Create a new Chroma collection with customizable HNSW parameters, embedding functions, and optional metadata to organize and manage AI-generated or user-input data efficiently.Apache 2.0
- Manage team settings, membership, BYOK credentials, API tokens, notifications, and KMS encryption keys. Write actions require owner or admin role.AGPL 3.0
- Extract specific code sections with line numbers from files. Saves context tokens by returning only relevant code instead of full file content.MIT
- Edit an existing note with four modes: full replace, append, find & replace, or section replacement. Supports dry run and atomic writes.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
- Search memories by text across labels, descriptions, and tags. Retrieve live entries with optional domain scoping or exact matching for identifiers.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
- 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