4,000+ servers built on vurb.ts
Vinkius

Open WebUI MCP Server for CursorGive Cursor instant access to 12 tools to Add File To Collection, Chat Completed, Chat Completions, and more

MCP Inspector GDPR Free for Subscribers

Cursor is an AI-first code editor built on VS Code that integrates LLM-powered coding assistance directly into the development workflow. Its Agent mode enables autonomous multi-step coding tasks, and MCP support lets agents access external data sources and APIs during code generation.

Ask AI about this MCP Server for Cursor

The Open WebUI MCP Server for Cursor is a standout in the Loved By Devs category — giving your AI agent 12 tools to work with, ready to go from day one.

Built for AI Agents by Vinkius

Vinkius delivers Streamable HTTP and SSE to any MCP client

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
Classic Setup·json
{
  "mcpServers": {
    "open-webui": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}
RecommendedModern Approach — Zero Configuration

Vinkius Desktop App

The modern way to manage MCP Servers — no config files, no terminal commands. Install Open WebUI and 4,000+ MCP Servers from a single visual interface.

Vinkius Desktop InterfaceVinkius Desktop InterfaceVinkius Desktop InterfaceVinkius Desktop Interface
Download Free Open SourceNo signup required
Open WebUI
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Open WebUI MCP Server

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

Cursor's Agent mode turns Open WebUI into an in-editor superpower. Ask Cursor to generate code using live data from Open WebUI and it fetches, processes, and writes. all in a single agentic loop. 12 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.

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.

The Open WebUI MCP Server exposes 12 tools through the Vinkius. Connect it to Cursor in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 12 Open WebUI tools available for Cursor

When Cursor connects to Open WebUI through Vinkius, your AI agent gets direct access to every tool listed below — spanning llm-management, rag, model-inference, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.

add

Add file to collection on Open WebUI

Add a file to a knowledge collection

chat

Chat completed on Open WebUI

Run outlet filters for completed chat

chat

Chat completions on Open WebUI

OpenAI-compatible chat completion

create

Create new chat on Open WebUI

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

get

Get file status on Open WebUI

Check file processing status

list

List models on Open WebUI

Retrieve all models

ollama

Ollama embed on Open WebUI

Ollama API Embeddings

ollama

Ollama generate on Open WebUI

Ollama API Generate Completion

ollama

Ollama tags on Open WebUI

List Ollama models

process

Process web url on Open WebUI

Process a web URL into a collection

send

Send message on Open WebUI

Anthropic-compatible message generation

upload

Upload file on Open WebUI

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

Connect Open WebUI to Cursor via MCP

Follow these steps to wire Open WebUI into Cursor. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.

01

Open MCP Settings

Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
02

Add the server config

Paste the JSON configuration above into the mcp.json file that opens
03

Save the file

Cursor will automatically detect the new MCP server
04

Start using Open WebUI

Open Agent mode in chat and ask: "Using Open WebUI, help me...". 12 tools available

Why Use Cursor with the Open WebUI MCP Server

Cursor AI Code Editor provides unique advantages when paired with Open WebUI through the Model Context Protocol.

01

Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context

02

Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards

03

MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment

04

VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools

Open WebUI + Cursor Use Cases

Practical scenarios where Cursor combined with the Open WebUI MCP Server delivers measurable value.

01

Code generation with live data: ask Cursor to generate a security report module using live DNS and subdomain data fetched through MCP

02

Automated documentation: have Cursor query your API's tool schemas and generate TypeScript interfaces or OpenAPI specs automatically

03

Infrastructure-as-code: Cursor can fetch domain configurations and generate corresponding Terraform or CloudFormation templates

04

Test scaffolding: ask Cursor to pull real API responses via MCP and generate unit test fixtures from actual data

Example Prompts for Open WebUI in Cursor

Ready-to-use prompts you can give your Cursor agent to start working with Open WebUI immediately.

01

"List all models available in my Open WebUI instance."

02

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

03

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

Troubleshooting Open WebUI MCP Server with Cursor

Common issues when connecting Open WebUI to Cursor through Vinkius, and how to resolve them.

01

Tools not appearing in Cursor

Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
02

Server shows as disconnected

Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.

Open WebUI + Cursor FAQ

Common questions about integrating Open WebUI MCP Server with Cursor.

01

What is Agent mode and why does it matter for MCP?

Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
02

Where does Cursor store MCP configuration?

Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
03

Can Cursor use MCP tools in inline edits?

No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
04

How do I verify MCP tools are loaded?

Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.

Explore More MCP Servers

View all →