How do I connect my Open WebUI instance?

You need to provide your Open WebUI Base URL and your API Key during the setup process on Vinkius.

Can I use local Ollama models?

Yes, this MCP includes specific capabilities to interact with the Ollama API for generation, tagging, and embeddings.

Does this work with Claude or Cursor?

Yes, once connected, you can use these capabilities from any MCP-compatible client including Claude, Cursor, and Windsurf.

How does the RAG functionality work?

You can upload files or process web URLs, which the MCP then stores in your Open WebUI collections for retrieval.

Is my data hosted by Vinkius?

Vinkius hosts the MCP and manages the connection, but the actual model execution and data storage happen on your Open WebUI instance.

How can I check if a model is available in my Open WebUI instance?

You can use the list_models capability. It will return a complete list of all configured models, including those from Ollama, OpenAI, and internal Open WebUI functions.

Can I add a website to my RAG collection using just a URL?

Yes! Use the process_web_url capability. Provide the URL and the target collection name, and the server will scrape and index the content for you.

How do I know when my uploaded file is ready for querying?

After using upload_file, you can check the ingestion progress by calling get_file_status with the returned File ID. It will tell you if the status is 'completed' or 'pending'.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Open WebUI to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Control local and cloud models from your favorite AI client.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 12 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 12 available through Open WebUI.

01
Ollama generate
This capability triggers a completion through the Ollama API. Use it to run local model inferences.
02
Chat completions
This capability provides an OpenAI-compatible interface for chat completions.
03
Create new chat
This capability starts a new backend-controlled chat session using unique message IDs.
04
Get file status
This capability checks the current processing state of a document you've uploaded for RAG.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 12 available through Open WebUI.

05
List models
This capability retrieves a full list of all available models in your Open WebUI instance.
06
Ollama embed
This capability generates embeddings using the Ollama API for local vector tasks.
07
Ollama tags
This capability lists all models currently available in your Ollama instance.
08
Process web URL
This capability scrapes a specific web URL and prepares it for use in a collection.

Capability set03 / 03

09-12

4 capabilities in this set.

Part of 12 available through Open WebUI.

09
Send message
This capability uses an Anthropic-compatible format to generate messages.
10
Upload file
This capability uploads a base64 encoded file to be extracted and stored in your vector database.
11
Add file to collection
This capability places an existing file into a specific knowledge collection.
12
Chat completed
This capability runs outlet filters once a chat completion is finished.

Real work

What teams actually run

Automated Documentation Ingestion

Feed a new documentation URL into a collection to immediately update your agent's knowledge.

Local Model Testing

Run specific prompts through local Ollama models to compare outputs with cloud models.

RAG Pipeline Management

Upload files and monitor their processing status to ensure your vector DB is ready for queries.

Unified Chat Interface

Use a single agent to manage chats across different backend providers like OpenAI or Anthropic.

Automate a task

Put Open WebUI to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Open WebUI works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Open WebUI to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

980ms average. Fast in production.

Open WebUI is checked daily against the live service.

Daily averagePeak 1245ms

Oct 3Today

Fastest day: 741ms
Slowest day: 1245ms
14-day trend: Stable+2%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 12 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Open WebUI, so you can see the experience inside your AI.

It does not authenticate your account with Open WebUI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Open WebUI Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_YhwRL8adKsCUXpVOwybG0l7vG8Iky4FGyj9DhmOn/mcp

Claude Desktop

Follow the steps below to connect in seconds.

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

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "open-webui-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_YhwRL8adKsCUXpVOwybG0l7vG8Iky4FGyj9DhmOn/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 Open WebUI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Open WebUI owners hand off.

This MCP is built for technical users who already run their own LLM infrastructure and want to use it within their development environments.

01
AI Engineers
They automate model testing and RAG configuration without switching to a browser.
02
Knowledge Managers
They ingest documentation and web data into collections via simple text commands.
03
DevOps Teams
They monitor local Ollama instances and manage model availability across teams.

FAQ

Questions Open WebUI owners ask.

01
How do I connect my Open WebUI instance?
You need to provide your Open WebUI Base URL and your API Key during the setup process on Vinkius.
02
Can I use local Ollama models?
Yes, this MCP includes specific capabilities to interact with the Ollama API for generation, tagging, and embeddings.
03
Does this work with Claude or Cursor?
Yes, once connected, you can use these capabilities from any MCP-compatible client including Claude, Cursor, and Windsurf.
04
How does the RAG functionality work?
You can upload files or process web URLs, which the MCP then stores in your Open WebUI collections for retrieval.
05
Is my data hosted by Vinkius?
Vinkius hosts the MCP and manages the connection, but the actual model execution and data storage happen on your Open WebUI instance.
06
How can I check if a model is available in my Open WebUI instance?
You can use the list_models capability. It will return a complete list of all configured models, including those from Ollama, OpenAI, and internal Open WebUI functions.
07
Can I add a website to my RAG collection using just a URL?
Yes! Use the process_web_url capability. Provide the URL and the target collection name, and the server will scrape and index the content for you.
08
How do I know when my uploaded file is ready for querying?
After using upload_file, you can check the ingestion progress by calling get_file_status with the returned File ID. It will tell you if the status is 'completed' or 'pending'.

Explore

More in Loved By Devs

Connect Open WebUI to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Ollama generate

Chat completions

Create new chat

Get file status

05-08

List models

Ollama embed

Ollama tags

Process web URL

09-12

Send message

Upload file

Add file to collection

Chat completed

What teams actually run

Automated Documentation Ingestion

Local Model Testing

RAG Pipeline Management

Unified Chat Interface

Building your own app? The connector is yours to use.

Open WebUI Connector

Claude Desktop

AI Engineers

Knowledge Managers

DevOps Teams

How do I connect my Open WebUI instance?

Can I use local Ollama models?

Does this work with Claude or Cursor?

How does the RAG functionality work?

Is my data hosted by Vinkius?

How can I check if a model is available in my Open WebUI instance?

Can I add a website to my RAG collection using just a URL?

How do I know when my uploaded file is ready for querying?

LibreChat AI Connector

VectorShift (AI Workflow & RAG Automation) AI Connector

LocalAI AI Connector

OpenAI AI Connector

Suggestions

Cockpit (Self-hosted Headless CMS API) AI Connector

Modelbit (ML Model Deployments) AI Connector

Mistral AI (Frontier LLMs & Embeddings) AI Connector

Ragas AI Connector