MCP servers by product
Ollama MCP servers
Ollama runs open large language models locally. 15 MCP Registry servers mention it in their own name or summary — 1 you can add by URL, 14 that run as a local package. Newest first.
- Servers
- 15
- Remote (add by URL)
- 1
- Local packages
- 14
A server listed here names the product in its registry entry; that does not make it official or tested. The publisher, repository and how to connect are on each server's page — check the publisher before connecting an assistant to an account.
| Server | Runs |
|---|---|
| Ask LlmUnified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity. | Local · stdio |
| Qsp ClientQSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM) | Local · stdio |
| Ask OllamaBridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local. | Local · stdio |
| Titan Frameworks (LangChain, LlamaIndex, Ollama, XRPL)Review and rewrite LangChain, LlamaIndex, Ollama, and XRPL code against current APIs. | Remote · HTTP |
| Cli Bridge MCPOther AI CLIs (Gemini, GPT, Claude, opencode, Ollama) as a council — ban-safe, no API keys. | Local · stdio |
| Ollama / vLLM BridgeCall your local Ollama or vLLM model over MCP with schema-validated JSON output. | Local · stdio |
| Algernon MCPFan a goal out to cheap parallel LLM workers on your own key or a free local Ollama. Keep your mind. | Local · stdio |
| ~alter mcp-ollamaWraps local Ollama models so bulk generation runs on your own hardware, not a paid API. | Local · stdio |
| Ollama HandoffOffload cheap work from your AI agent to a local Ollama model, at zero cloud cost. | Local · stdio |
| Obsidian Semantic SearchRead-only semantic search MCP server for Obsidian vaults using local Ollama embeddings. | Local · stdio |
| MCPBridgeUnified MCP server bridging Claude Code and Ollama to Roblox Studio and Blender. | Local · stdio |
| fish-bridge — Session Knowledge GraphCompresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama. | Local · stdio |
| Agentic ResearchLocal research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query. | Local · stdio |
| Claude Token Saver MCPMCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens. | Local · stdio |
| Massive Context MCPHandles 10M+ token contexts with chunking, sub-queries, and local Ollama inference. | Local · stdio |