[GH-ISSUE #645] issue: (Docs) Cannot find in API documentation whether (or not) MCP tools can be enabled in API calls #91

New issue

Closed

opened 2026-10-18 14:08:55 +00:00 by bsakaguchi · 1 comment

bsakaguchi commented

2026-10-18 14:08:55 +00:00

Owner

Originally created by @helicalchris on GitHub (Aug 7, 2025).
Original GitHub issue: https://github.com/open-webui/docs/issues/645

Check Existing Issues

I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

0.6.18

Ollama Version (if applicable)

latest

Operating System

docker on Sonoma

Browser (if applicable)

No response

Confirmation

I have read and followed all instructions in README.md.
I am using the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.
I have provided every relevant configuration, setting, and environment variable used in my setup.
I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
Start with the initial platform/version/OS and dependencies used,
Specify exact install/launch/configure commands,
List URLs visited, user input (incl. example values/emails/passwords if needed),
Describe all options and toggles enabled or changed,
Include any files or environmental changes,
Identify the expected and actual result at each stage,
Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

I am trying to ascertain whether the API allows the use of web searches and MCP tools in the same way that you can launch queries through API calls. The docs are silent on external connections and for the life of me I can't get Swagger API docs to work on my docker container. I got really excited about Claude giving me an API call that did it but I think it just hallucinated the ability as it doesn't work (but I can fix as I can't find a reference to fix it with). Apologies if issues with docs shouldn't be raised this way, or indeed I just haven't read the right bit)

Actual Behavior

Docs detail or exclude external connections via API. I had expected it to be exposed in the same kind of way that knowledge and files are exposed.

Steps to Reproduce

N/A, docs related issue

Logs & Screenshots

N/A, docs related issue

Additional Information

No response

Originally created by @helicalchris on GitHub (Aug 7, 2025). Original GitHub issue: https://github.com/open-webui/docs/issues/645 ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version 0.6.18 ### Ollama Version (if applicable) latest ### Operating System docker on Sonoma ### Browser (if applicable) _No response_ ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior I am trying to ascertain whether the API allows the use of web searches and MCP tools in the same way that you can launch queries through API calls. The docs are silent on external connections and for the life of me I can't get Swagger API docs to work on my docker container. I got really excited about Claude giving me an API call that did it but I think it just hallucinated the ability as it doesn't work (but I can fix as I can't find a reference to fix it with). _Apologies if issues with docs shouldn't be raised this way, or indeed I just haven't read the right bit)_ ### Actual Behavior Docs detail or exclude external connections via API. I had expected it to be exposed in the same kind of way that knowledge and files are exposed. ### Steps to Reproduce N/A, docs related issue ### Logs & Screenshots N/A, docs related issue ### Additional Information _No response_

bsakaguchi

2026-10-18 14:08:55 +00:00

closed this issue
added the
bug
label

bsakaguchi commented

2026-10-18 14:08:56 +00:00

Author

Owner

@helicalchris commented on GitHub (Aug 9, 2025):

Adding to this, I also just discovered the tools and functions area of the openwebui site and that opened my eyes to capability extension. This makes me stand by the fact that openwebui is the best front end to self hosting (or even cloud hosted) by miles, but it's just a pity to then have to replicate this capability in a second platform like N8n for other tools (like plugins into MS Word) that need to use more than just plain query/response, and if you make it in API it kind of defeats the point of openwebui running alongside! A full API access to give parity to the UI would be amazing

@helicalchris commented on GitHub (Aug 9, 2025): Adding to this, I also just discovered the tools and functions area of the openwebui site and that opened my eyes to capability extension. This makes me stand by the fact that openwebui is the best front end to self hosting (or even cloud hosted) by miles, but it's just a pity to then have to replicate this capability in a second platform like N8n for other tools (like plugins into MS Word) that need to use more than just plain query/response, and if you make it in API it kind of defeats the point of openwebui running alongside! A full API access to give parity to the UI would be _amazing_