Connect Ollama to ChatGPT, Claude and Gemini

• 01 / 03How to build local RAG
• 02 / 03How to extract data
• 03 / 03How to manage local models

Fastest day

764ms

Slowest day

1115ms

14-day trend

Stable-4%

Ollama Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_hYpu67YLXAzJ2w17TRhdjXKZcyynLB0AY9L4fYBJ/mcpCopy

Claude Desktop

Follow the steps below to connect in seconds.

1. 1In Claude Desktop, open Settings → Connectors.
2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3. 3Click Add and start a new chat — Ollama capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "ollama-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_hYpu67YLXAzJ2w17TRhdjXKZcyynLB0AY9L4fYBJ/mcp"
    }
  }
}

• Claude
• ChatGPT
• Cursor
• VS Code
• Windsurf
• Claude Code
• JetBrains
• Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Ollama in Claude and other AIs

See all the AI clients this connector works with ↑

• 01

  AI Engineers

  They use this to test model capabilities and compare outputs across different local models.

• 02

  Developers

  They use this to prototype with various LLMs using natural language instead of manual API calls.

• 03

  Data Teams

  They use this to generate embeddings for RAG pipelines and semantic search.

• 01

  How do I get my Ollama API key?

  Visit the Ollama API keys page to create or manage your API key. Once created, copy it and paste it into the API key field in the setup wizard. The key is used as a Bearer token in the Authorization header for all requests to https://ollama.com/api. API keys don't currently expire, but you can revoke them at any time.

• 02

  Which models are available through this MCP?

  All models available on ollama.com are accessible, including Gemma, GPT-OSS, Qwen, Llama, and many others. Use list_models to see all available models, and show_model_details to inspect a model's capabilities (completion, vision, capabilities), parameter size, quantization level, and architecture details.

• 03

  Can my AI use vision models to analyze images?

  Yes! The generate and chat capabilities support image inputs as base64-encoded strings. Use a vision-capable model (check with show_model_details. look for 'vision' in capabilities) and pass images in the request. The OpenAI-compatible openai_chat_completions capability also supports image_url content parts for vision models.

• 04

  What is the difference between native and OpenAI-compatible endpoints?

  The native Ollama endpoints (generate, chat, embed) offer the full feature set including thinking mode, keep_alive control, and detailed response metadata (token counts, durations). The OpenAI-compatible endpoints (/v1/chat/completions, /v1/completions, /v1/embeddings, /v1/responses) provide drop-in compatibility for existing applications built with the OpenAI SDK. they use the same request/response format as OpenAI's API.

• 05

  Does this MCP support capability calling (function calling)?

  Yes. The chat capability supports capability calling. pass a JSON array of capability definitions in the tools_json parameter. The model will return capability calls in the response when it determines a function should be invoked. The OpenAI-compatible openai_chat_completions capability also supports capabilities via the tools_json parameter.

• 06

  Can I generate structured JSON output?

  Yes. Both generate and chat capabilities support structured outputs via the format_json parameter. You can pass the string 'json' for basic JSON mode, or a full JSON schema object to enforce a specific output structure. The OpenAI-compatible endpoints also support response_format for structured output.

• 07

  What is the base URL for API calls?

  All API calls are sent to https://ollama.com/api with the Authorization: Bearer YOUR_API_KEY header. The engine automatically appends the correct path for each endpoint (e.g. /generate, /chat, /v1/chat/completions). This MCP targets the Ollama cloud API. for local Ollama instances, the base URL would be http://localhost:11434/api (no API key required).

• 

  Mistral AI (Frontier LLMs & Embeddings) AI Connector

  Manage AI inference via Mistral — execute chat completions, generate RAG embeddings, and audit frontier models

  View
• 

  LangSmith (LLM Observability & Hub) AI Connector

  Monitor LLM apps via LangSmith — track traces, audit prompt templates, and manage evaluation datasets.

  View
• 

  Langfuse (LLM Tracing & Evals) AI Connector

  Monitor LLM apps via Langfuse — track traces, manage prompt templates, and audit evaluation scores.

  View
• 

  LocalAI AI Connector

  Run LLMs, generate images, and process audio locally. OpenAI-compatible API for your own hardware.

  View

Suggestions

• 

  LLM Token Counter AI Connector

  Calculate exact and estimated token counts for GPT-4, GPT-4o, Claude, and Llama models.

  View
• 

  DeepInfra (Serverless LLM Inference) AI Connector

  Run top-tier LLMs, image generation, and embeddings via DeepInfra's serverless infrastructure directly from yo

  View
• 

  Voyage AI (AI Embeddings API) AI Connector

  Generate high-quality text, multimodal, and contextualized embeddings, plus high-precision reranking for RAG w

  View
• 

  OpenAI AI Connector

  Use GPT-4o, DALL-E 3, embeddings, fine-tuning, and moderation as tools inside your AI agent workflows.

  View