0n3
MCP servers · ai

Ollama MCP server

Local AI inference — chat completions, embeddings, model management. Free, private, no API costs.. Hosted by 0n3: 8 endpoints your AI can call with your own Ollama account, from Claude, ChatGPT, Cursor, Claude Code, Codex or Gemini CLI. One sign-in, one key per AI, a receipt for every call.

Connect OllamaInstall into your AIWatch it work

8 endpoints5 categoriesauth: nonehosted

What your AI can do with Ollama

Generate text · Generate text completions with local models (Llama, Mistral, etc.)1
GeneratePOST /api/generate
Chat completion · Multi-turn chat with local models1
Chat completionPOST /api/chat
Create embedding · Create text embeddings locally1
Create an embeddingPOST /api/embed
Models · List, pull, inspect, and delete local models4
List modelsGET /api/tags
Show modelPOST /api/show
Pull modelPOST /api/pull
Delete a modelDELETE /api/delete
More · Everything else this app exposes.1
List runningGET /api/ps

Install in three steps

  1. Create a free account at 0n3.app and connect Ollama: paste a key or sign in through a door. It lands in your vault, encrypted.
  2. Open 0n3.app/install, pick your AI. A key is made for that AI alone; copy the line it gives you.
  3. Ask your AI: whoami. It answers with your connected services. Then ask it to generate in Ollama.
Install (user scope — every project)
claude mcp add --transport http --scope user 0n3 https://0n3.app/mcp --header "Authorization: Bearer <your 0n token>"

Connect Ollama to

Claude Code + OllamaMCP server + skillClaude (desktop & claude.ai) + OllamaconnectorChatGPT + Ollamaconnector · GPT actionCodex CLI + OllamaMCP serverGemini CLI + OllamaMCP serverCursor + OllamaMCP serverVS Code (Copilot) + OllamaMCP serverWindsurf + OllamaMCP server

More ai MCP servers

ElevenLabs8 endpointsReplicate8 endpointsDeepgram7 endpointsCohere6 endpointsStability AI6 endpointsOpenAI4 endpointsGroq3 endpointsMistral3 endpoints

Questions

What can an AI do with the Ollama MCP server?

8 things: generate text, chat completion, create embedding, models and more. Every call runs with your own Ollama connection and lands on a receipt.

Do I need to run anything on my computer?

No. 0n3 is hosted. Connect Ollama once, install 0n3 into your AI with one line, done.

Where does my Ollama key go?

Into your 0n3 vault, encrypted, one record per connection. The AI never sees it.