Ollama Connector for AI agents.
12 live capabilities
Run local LLMs and generate vector embeddings for your private data.
Waiting for input…
Why people use Ollama
Ollama for Local LLM Inference and Privacy
This Connector puts your local models directly into your agent's hands. You just point your client at your Ollama setup and start talking to your own weights. You get the speed of local execution with the ease of a chat interface that feels like a natural extension of your current setup.
What Vinkius changes
You get a direct line to your local model library without any extra coding.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Building a private RAG
You need to index internal docs.
- Real-world use case 02
Testing local weights
You want to see if Qwen handles your specific task better than Llama.
- Real-world use case 03
Vision-based analysis
You need to describe images in a batch.
Complete set · 12capabilities
The complete Ollama capability set.
These are the exact actions your AI can choose when you ask it to work with Ollama.
01—04
4 capabilities in this set.
Part of 12 available through Ollama.
- 01 Capability
Openai chat completions
Generate chat completions using an OpenAI-compatible endpoint. It supports vision and capability calling.
- 02 Capability
Openai completions
Use the OpenAI-compatible completion endpoint for your existing workflows. It supports various stop sequences.
- 03 Capability
Openai embeddings
Generate embeddings via an OpenAI-compatible endpoint. It's a drop-in replacement for standard embedding calls.
- 04 Capability
Openai list models
Get model IDs and ownership info using the OpenAI-compatible list endpoint. This is great for existing SDK users.
05—08
4 capabilities in this set.
Part of 12 available through Ollama.
- 05 Capability
Openai responses
Use the OpenAI-compatible Responses API to generate full responses. It works with your existing OpenAI-style logic.
- 06 Capability
List models
Get a full list of all models you have downloaded. Use this to see what's ready to run.
- 07 Capability
List running models
See which models are currently loaded in your VRAM. It shows the model size and when they'll be unloaded.
- 08 Capability
Chat
Send multimodal messages and get structured JSON responses from your models. It handles images and capability calling in one go.
09—12
4 capabilities in this set.
Part of 12 available through Ollama.
- 09 Capability
Generate embeddings
Generate vector embeddings from single or multiple text inputs. This is perfect for building your own RAG pipelines.
- 10 Capability
Generate
Generate text completions with full control over parameters like seed and temperature. It supports structured JSON outputs too.
- 11 Capability
Get version
Retrieve the version of your local environment. Use this to ensure compatibility with your current capabilities.
- 12 Capability
Show model details
Get the deep specs for a specific model. You can check parameters, quantization, and tokenizer settings here.
Set up in minutes
One URL. Then ask Ollama to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Ollama from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_hYpu67YLXAzJ2w17TRhdjXKZcyynLB0AY9L4fYBJ/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Ollama, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Ollama for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_hYpu67YLXAzJ2w17TRhdjXKZcyynLB0AY9L4fYBJ/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Ollama URL.
- Step 03
Save and start
Save the connection and enable Ollama in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"ollama": {
"url": "https://edge.vinkius.com/vk_preview_hYpu67YLXAzJ2w17TRhdjXKZcyynLB0AY9L4fYBJ/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Ollama
Open Agent mode in chat and ask: "Using Ollama, help me...". 12 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"ollama": {
"url": "https://edge.vinkius.com/vk_preview_hYpu67YLXAzJ2w17TRhdjXKZcyynLB0AY9L4fYBJ/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Ollama
Ask Copilot: "Using Ollama, help me...". 12 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"ollama": {
"url": "https://edge.vinkius.com/vk_preview_hYpu67YLXAzJ2w17TRhdjXKZcyynLB0AY9L4fYBJ/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Ollama
Open Cascade and ask: "Using Ollama, help me...". 12 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"ollama": {
"url": "https://edge.vinkius.com/vk_preview_hYpu67YLXAzJ2w17TRhdjXKZcyynLB0AY9L4fYBJ/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Ollama
Ask Cline: "Using Ollama, help me...". 12 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add ollama --transport http "https://edge.vinkius.com/vk_preview_hYpu67YLXAzJ2w17TRhdjXKZcyynLB0AY9L4fYBJ/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Ollama
Ask Claude: "Using Ollama, show me...". 12 tools are ready
Where the request belongs
Work Ollama can move forward.
This is for the developer who needs to keep data local, the AI engineer testing specific weights, or the data scientist building a custom RAG pipeline.
AI Engineer
Testing model outputs and comparing performance across different local weights on a Tuesday afternoon.
Data Scientist
Generating embeddings for high-volume vector databases for a new search feature.
Privacy-Focused Developer
Running sensitive tasks on-premise to ensure no data ever leaves the local machine.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsDeepInfra (Serverless LLM Inference)
Run top-tier LLMs, image generation, and embeddings via DeepInfra's serverless infrastructure directly from your AI agent.
Together AI
Generate code, evaluate embeddings, and deploy open-source LLMs instantly from your local agent via Together AI's infrastructure.
OpenAI
Manage OpenAI resources via API. list models, monitor fine-tunes, manage batches and inspect Assistants from any AI agent.
Groq
Run large language models at unprecedented speed with custom LPU hardware that delivers real-time AI inference at massive scale.
Mistral AI (Frontier LLMs & Embeddings)
Manage AI inference via Mistral. execute chat completions, generate RAG embeddings, and audit frontier models.
SambaNova (AI Inference)
High-speed AI inference for Llama 3, DeepSeek, and MiniMax models via SambaNova's ultra-fast SN40L chips.
Bring your own AI
Change the model, client or framework. Keep Ollama connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Ollama.
The practical details behind the request, access and result.
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.
Which models are available through this Connector?
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.
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.
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.
Does this Connector 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.
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.
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 Connector targets the Ollama cloud API. for local Ollama instances, the base URL would be http://localhost:11434/api (no API key required).
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.
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.
One connection away
Give your agent a direct line to Ollama.
Connect Ollama once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available