I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Docker
Open WebUI Version
0.6.15
Ollama Version (if applicable)
No response
Operating System
Synology DSM 7.2
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 created a model and enabled tool(mcp). When calling the model through the api, the model can call tool(mcp) correctly.
Actual Behavior
I created a model and enabled tool(mcp). But when calling the model through the api, the model does not call tool(mcp) correctly.
Steps to Reproduce
I created a model and enabled the tool (mcp).
Requested the model to process task A through the open-webui interface
I could see the request in the mcpo log
Requested the model to process the same task A through the api
There was no request in the mcpo log
Logs & Screenshots
No response
Additional Information
No response
Originally created by @guoaen on GitHub (Jul 2, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/15471
### 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
0.6.15
### Ollama Version (if applicable)
_No response_
### Operating System
Synology DSM 7.2
### 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 created a model and enabled tool(mcp). When calling the model through the api, the model can call tool(mcp) correctly.
### Actual Behavior
I created a model and enabled tool(mcp). But when calling the model through the api, the model does not call tool(mcp) correctly.
### Steps to Reproduce
1. I created a model and enabled the tool (mcp).
2. Requested the model to process task A through the open-webui interface
3. I could see the request in the mcpo log
4. Requested the model to process the same task A through the api
5. There was no request in the mcpo log
### Logs & Screenshots
No response
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-04-25 06:58:18 -05:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @guoaen on GitHub (Jul 2, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/15471
Check Existing Issues
Installation Method
Docker
Open WebUI Version
0.6.15
Ollama Version (if applicable)
No response
Operating System
Synology DSM 7.2
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
I created a model and enabled tool(mcp). When calling the model through the api, the model can call tool(mcp) correctly.
Actual Behavior
I created a model and enabled tool(mcp). But when calling the model through the api, the model does not call tool(mcp) correctly.
Steps to Reproduce
Logs & Screenshots
No response
Additional Information
No response
@tjbck commented on GitHub (Jul 2, 2025):
We're unable to reproduce with the information provided, keep us updated.