Open WebUI

Open WebUI MCP Connector for Claude

A+

Manage your Open WebUI instance — list models, handle chat completions, and manage RAG collections directly from any AI agent.

12 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Open WebUI instance to any AI agent and take full control of your local and cloud LLM orchestration through natural conversation.

What you can do

  • Model Management — Use list_models to fetch all available models including Ollama, OpenAI, and Open WebUI Functions.
  • RAG & Knowledge Base — Upload files with upload_file, process web content via process_web_url, and organize them into collections using add_file_to_collection.
  • Chat Orchestration — Create and manage backend-controlled chats with create_new_chat or use OpenAI/Anthropic compatible endpoints like chat_completions and send_message.
  • Native Ollama Support — Directly interact with the Ollama API using ollama_generate, ollama_tags, and ollama_embed for local inference tasks.
  • File Processing — Monitor the status of your document ingestion with get_file_status to ensure your RAG context is ready.

How it works

  1. Subscribe to this server
  2. Enter your Open WebUI Base URL and API Key
  3. Start managing your LLM infrastructure from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI Engineers — automate the testing of different models and RAG configurations without leaving the terminal or IDE.
  • Knowledge Managers — quickly ingest documentation and web URLs into Open WebUI collections via simple commands.
  • DevOps Teams — monitor local Ollama instances and manage model availability across the organization.
llm-managementragmodel-inferenceself-hostedchat-interfaceautomation

12 tools expose this connector's capabilities to your AI agent.

add_file_to_collection

Add a file to a knowledge collection

chat_completed

Run outlet filters for completed chat

chat_completions

OpenAI-compatible chat completion

create_new_chat

Must generate UUIDs for message IDs. Create a new chat (Backend-Controlled Flow)

get_file_status

Check file processing status

list_models

Retrieve all models

ollama_embed

Ollama API Embeddings

ollama_generate

Ollama API Generate Completion

ollama_tags

List Ollama models

process_web_url

Process a web URL into a collection

send_message

Anthropic-compatible message generation

upload_file

Content is extracted and stored in the vector DB. Provide file content as base64. Upload a file for RAG

See how to talk to your AI agent using Open WebUI.

List all models available in my Open WebUI instance.

I've retrieved the models. You have access to 'llama3:latest', 'gpt-4o', and several custom Open WebUI functions. Would you like to use one of them for a chat completion?

Process the URL 'https://docs.openwebui.com/' into my 'Documentation' collection.

I have started processing the URL. The content is being scraped and indexed into the 'Documentation' collection. You can now ask questions based on this data.

Generate a response using the 'llama3' model for the prompt 'Explain quantum computing'.

Using the `ollama_generate` tool with 'llama3': Quantum computing is a type of computing that uses quantum-mechanical phenomena... Would you like more details?

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

Related Connectors