openwebui-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Set to 'openwebui-mcp' to log HTTP requests to stderr | |
| OPENWEBUI_URL | Yes | Base URL of Open WebUI instance (e.g. http://localhost:3000) | |
| OPENWEBUI_API_KEY | Yes | Bearer token from Open WebUI Settings -> Account -> API Keys |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| 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. |
| openwebui_search_chatsA | Search chat history by keyword. Searches through chat titles and message content. Returns matching conversations with IDs. |
| 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. |
| openwebui_delete_chatA | Delete a specific chat by ID. This is irreversible. Requires confirm: true. |
| openwebui_get_chat_tagsA | List all tags used across chats in Open WebUI. Useful for understanding how conversations are organized. |
| openwebui_list_knowledgeA | List all RAG knowledge base collections in Open WebUI. Returns collection names, IDs, descriptions, and file counts. |
| openwebui_get_knowledgeA | Get details of a specific knowledge base including its name, description, and the list of files it contains. |
| 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. |
| openwebui_update_knowledgeA | Update a knowledge base name or description. Does not affect files already in the collection. |
| openwebui_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. |
| 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. |
| 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. |
| 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. |
| openwebui_get_file_infoA | Get metadata about a specific uploaded file — name, size, content type, and creation date. Does not return file content. |
| 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. |
| openwebui_list_functionsA | List all Pipe, Filter, and Action functions installed in Open WebUI. Returns function IDs, names, types, and enable/disable status. |
| openwebui_get_functionA | Get full details of a specific function including its Python source code and configuration. |
| 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. |
| openwebui_update_functionA | Update an existing function's source code, name, or description. Pass only the fields you want to change. |
| openwebui_delete_functionA | Delete a function from Open WebUI. This removes the function permanently. Requires confirm: true. |
| 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. |
| 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. |
| 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"). |
| openwebui_update_promptA | Update an existing saved prompt's name or content. The command (trigger) cannot be changed — delete and recreate instead. |
| openwebui_delete_promptA | Delete a saved prompt by its command. Requires confirm: true. |
| openwebui_get_statusA | Check Open WebUI system status, version, and health. Useful for verifying connectivity and confirming which version is running. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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.