openwebui-mcp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@openwebui-mcp-server Search my chats for Kubernetes networking"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Open WebUI MCP Server
Connect Claude Code and Claude Desktop to your Open WebUI instance. Manage chats, RAG knowledge bases, files, functions, and prompts — directly from Claude.
What This Does
Open WebUI is a powerful self-hosted AI interface — but until now, you couldn't interact with it from Claude. This MCP server bridges that gap.
Once connected, Claude can search your chat history, build RAG knowledge bases from files you describe, create custom pipeline functions, and manage prompts — all without leaving your conversation.
Who it's for: Claude Code users, Claude Desktop users, AI developers, and Open WebUI power users who want Claude to help manage their AI infrastructure.
Related MCP server: opennms-mcp
Quick Start
Claude Code (3 commands)
# 1. Get your API key from Open WebUI: Settings → Account → API Keys
# 2. Add the MCP server
claude mcp add openwebui \
-e OPENWEBUI_URL=http://localhost:3000 \
-e OPENWEBUI_API_KEY=sk-your-key-here \
-- npx -y openwebui-mcp-server
# 3. Verify it's connected
# In Claude Code, run: /mcpClaude Desktop
Paste this into your claude_desktop_config.json:
{
"mcpServers": {
"openwebui": {
"command": "npx",
"args": ["-y", "openwebui-mcp-server"],
"env": {
"OPENWEBUI_URL": "http://localhost:3000",
"OPENWEBUI_API_KEY": "your-api-key-here"
}
}
}
}Config file locations:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
Available Tools (23 total)
Chats
Tool | Description |
| List recent conversations, paginated |
| Search chat history by keyword |
| Get full chat with all messages |
| Delete a chat (requires confirm) |
| List all tags used across chats |
Knowledge Bases (RAG)
Tool | Description |
| List all knowledge base collections |
| Get collection details and file list |
| Create a new collection |
| Update name or description |
| Add uploaded file to a collection |
| Remove file from a collection |
Files
Tool | Description |
| List all uploaded files |
| Upload file (base64 content) |
| Get file metadata |
| Delete a file (requires confirm) |
Functions (Pipes, Filters, Actions)
Tool | Description |
| List all functions by type |
| Get function with source code |
| Create a new Python function |
| Update function code or metadata |
| Delete a function (requires confirm) |
Models
Tool | Description |
| List all available models |
Prompts
Tool | Description |
| List all saved prompts |
| Create a new saved prompt |
| Update prompt title or content |
| Delete a prompt (requires confirm) |
System
Tool | Description |
| Check health, version, and config |
Configuration
Variable | Required | Description |
| Yes | Base URL (e.g. |
| Yes | Bearer token from Settings → Account → API Keys |
| No | Set to |
Examples
Build a RAG knowledge base
"Create a knowledge base called 'Security Runbooks' for incident response docs"
→ openwebui_create_knowledge(name: "Security Runbooks", ...)
Knowledge base created. ID: abc-123
"Upload this runbook and add it to Security Runbooks"
→ openwebui_upload_file(filename: "incident-response.md", ...)
→ openwebui_add_file_to_knowledge(knowledge_id: "abc-123", file_id: "xyz-456")
File added. Now available for RAG retrieval.Search and review conversations
"Search my chats for any discussion about Kubernetes networking"
→ openwebui_search_chats(query: "kubernetes networking")
Found 3 chats: [list of results]
"Show me the full conversation from last week about DNS issues"
→ openwebui_get_chat(id: "...")
[Full conversation displayed]Create a reusable prompt
"Create a prompt /standup that generates a standup update from {{input}}"
→ openwebui_create_prompt(
command: "/standup",
title: "Daily Standup",
content: "Generate a concise standup update from these notes: {{input}}"
)
Prompt created. Type /standup in any Open WebUI chat to use it.Install a custom pipe function
"Create a pipe function that translates all responses to French"
→ openwebui_create_function(
id: "french_translator",
name: "French Translator",
type: "filter",
content: "# Python code..."
)
Function created. Enable it in Settings → Functions.Requirements
Node.js >= 18.0.0
Open WebUI >= 0.3.0 (any self-hosted install)
API key from Open WebUI Settings → Account → API Keys
Contributing
See CONTRIBUTING.md for guidelines.
Issues and PRs welcome — especially for new API endpoints added in newer Open WebUI versions.
License
MIT — see LICENSE
Built by Marc — cybersecurity and automation infrastructure at CyberLeda
Available Tools
26 toolsopenwebui_add_file_to_knowledgeA
Add an uploaded file to a knowledge base for RAG retrieval. The file must already be uploaded via openwebui_upload_file. Get the file ID from the upload response.
Inputs: file_id (required), knowledge_id (required).
openwebui_create_functionA
Create a new Pipe, Filter, or Action function in Open WebUI. Pipes add new model options. Filters transform messages. Actions add chat toolbar buttons. Provide valid Python code.
Inputs: id (required), name (required), type (required), content (required), +1 more.
openwebui_create_knowledgeA
Create a new RAG knowledge base collection. After creating, use openwebui_upload_file and openwebui_add_file_to_knowledge to populate it.
Inputs: name (required), description.
openwebui_create_promptA
Create a new saved prompt in Open WebUI. Prompts are invoked by typing their command in any chat. Command must start with "/" (e.g. "/summarize").
Inputs: name (required), command (required), content (required).
openwebui_delete_chatA
Delete a specific chat by ID. This is irreversible. Requires confirm: true.
Inputs: id (required), confirm (required).
openwebui_delete_fileA
Permanently delete an uploaded file from Open WebUI. If the file is in a knowledge base, remove it from the collection first with openwebui_remove_file_from_knowledge. Requires confirm: true.
Inputs: id (required), confirm (required).
openwebui_delete_functionA
Delete a function from Open WebUI. This removes the function permanently. Requires confirm: true.
Inputs: id (required), confirm (required).
openwebui_delete_promptA
Delete a saved prompt by its command. Requires confirm: true.
Inputs: command (required), confirm (required).
openwebui_get_chatA
Get full details of a specific chat by ID, including all messages in the conversation. Use openwebui_list_chats or openwebui_search_chats to find chat IDs.
Inputs: id (required).
openwebui_get_chat_tagsA
List all tags used across chats in Open WebUI. Useful for understanding how conversations are organized.
Inputs: no named parameters.
openwebui_get_file_infoA
Get metadata about a specific uploaded file — name, size, content type, and creation date. Does not return file content.
Inputs: id (required).
openwebui_get_functionA
Get full details of a specific function including its Python source code and configuration.
Inputs: id (required).
openwebui_get_knowledgeA
Get details of a specific knowledge base including its name, description, and the list of files it contains.
Inputs: id (required).
openwebui_get_statusA
Check Open WebUI system status, version, and health. Useful for verifying connectivity and confirming which version is running.
Inputs: no named parameters.
openwebui_list_chatsA
List recent chat conversations in Open WebUI. Returns up to 50 chats per page with title, ID, and last update time. Use page parameter to paginate.
Inputs: page.
openwebui_list_filesA
List all files uploaded to Open WebUI. Returns file names, IDs, sizes, and content types. Use file IDs with openwebui_add_file_to_knowledge.
Inputs: no named parameters.
openwebui_list_functionsA
List all Pipe, Filter, and Action functions installed in Open WebUI. Returns function IDs, names, types, and enable/disable status.
Inputs: no named parameters.
openwebui_list_knowledgeA
List all RAG knowledge base collections in Open WebUI. Returns collection names, IDs, descriptions, and file counts.
Inputs: no named parameters.
openwebui_list_modelsA
List all available models in Open WebUI — includes Ollama local models, OpenAI models, and custom pipe models. Returns model IDs, names, and sources.
Inputs: no named parameters.
openwebui_list_promptsA
List all saved prompts in Open WebUI. Prompts are reusable message templates triggered by commands like "/summarize". Returns command, title, and a content preview.
Inputs: no named parameters.
openwebui_remove_file_from_knowledgeA
Remove a file from a knowledge base. The file itself is not deleted — only removed from this collection. Use openwebui_delete_file to delete the file entirely.
Inputs: file_id (required), knowledge_id (required).
openwebui_search_chatsA
Search chat history by keyword. Searches through chat titles and message content. Returns matching conversations with IDs.
Inputs: query (required).
openwebui_update_functionA
Update an existing function's source code, name, or description. Pass only the fields you want to change.
Inputs: id (required), name, content, description.
openwebui_update_knowledgeA
Update a knowledge base name or description. Does not affect files already in the collection.
Inputs: id (required), name, description.
openwebui_update_promptA
Update an existing saved prompt's name or content. The command (trigger) cannot be changed — delete and recreate instead.
Inputs: command (required), name, content.
openwebui_upload_fileA
Upload a file to Open WebUI. Accepts base64-encoded content (required for MCP stdio transport). After uploading, use the returned file ID with openwebui_add_file_to_knowledge to add it to a RAG collection.
Inputs: filename (required), base64_content (required), content_type.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 26 tools
Every tool targets a distinct resource and action. Even similar operations like removing a file from knowledge vs deleting the file are clearly differentiated in descriptions. No two tools appear to do the same thing.
All tool names follow the consistent pattern `openwebui_<verb>_<noun>`. Verbs and nouns are used systematically, with list tools using plural nouns and singular object tools using singular nouns, maintaining a clear and predictable convention.
At 26 tools, the count is on the higher end, but the server covers seven distinct resource areas (chats, knowledge, files, functions, prompts, models, status). Each tool has a clear purpose, though some consolidation could be possible. Overall it's slightly over the ideal range but justified by scope.
Most core workflows are covered: chats have list/search/get/delete, files have full lifecycle, functions have full CRUD, and knowledge has create/update/add/remove. However, missing knowledge base deletion and prompt detail retrieval are notable gaps, and model operations are limited to listing only.
Maintenance
Related MCP Connectors
Connect Claude to your Platform7n workspaces: chat, links, work and decks. One-click OAuth.
Connect Claude to your Platform7n workspaces: chat, links, work and decks. One-click OAuth.
One workspace of tools for Claude and ChatGPT: connect 600+ apps, generate media, build tools.
Create projects, nodes, and tasks in UluP Spaces by conversation with Claude.
Related MCP Servers
- AlicenseBqualityDmaintenanceConnects Claude to a Wiki.js instance, enabling page search, retrieval, listing, and creation.48 npmMIT
- FlicenseNot gradedqualityDmaintenanceConnects Claude to OpenNMS, allowing plain language interaction with alarms, nodes, events, asset records, categories, and service collection.1-
- AlicenseAqualityDmaintenanceConnects Claude Desktop to an Obsidian vault, enabling reading, searching, capturing ideas, and managing notes through natural language.213 npmMIT
- AlicenseNot gradedqualityCmaintenanceConnects Claude to a local Obsidian vault, enabling listing, reading, searching, and optionally editing notes via natural language, with all operations running locally.MIT