Open WebUI integrations

Documented connections between Open WebUI and model servers, tool servers, search, speech, image and observability services.

Open WebUI with vLLM

Serving models on GPU servers with vLLM and connecting them to Open WebUI through the OpenAI-compatible API, including timeouts during model loading and when to put LiteLLM in between.

Open WebUI MCP tool servers

Connecting MCP servers over streamable HTTP with OAuth 2.1, why only admins can add them, the WEBUI_SECRET_KEY requirement, and how MCP differs from user-added OpenAPI tool servers.

Open WebUI with OneDrive and SharePoint

Letting users attach files from OneDrive for Business and SharePoint in Open WebUI chats: Entra ID app registration, environment variables and the separate personal OneDrive option.

Open WebUI web search with SearXNG

Adding web search to Open WebUI with a self-hosted SearXNG instance instead of a paid search API, and the trade-offs against hosted providers such as Brave or Tavily.

Open WebUI image generation with ComfyUI

Connecting Open WebUI to a self-hosted ComfyUI or AUTOMATIC1111 server for image generation and editing inside chat, versus hosted OpenAI or Gemini image models.

Talk to our team.

Tell us what you're working on, whether it's a deployment, an audit, a security test or a cyber range. You'll speak with an engineer who can help you scope it.

  • 30-minute call: free, with no obligation.
  • NDA on request: we can sign before you share details.
  • Clear next steps: a scope and plan after the call.
Book a callhello@deployopen.com