GLM_
1 MCP server offers this tool
What it usually takes
effort– in 1 of 1history– in 1 of 1image_path– in 1 of 1message– in 1 of 1system_prompt– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
GLM-5.3-Flash Vision co.huggingface.piggyyuzai/glm-5.3-flash-vision Stream a multimodal reply from GLM-5.3-Flash for text and an optional image. Inputs: chat text, optional uploaded image path, prior chat history, system prompt, reasoning effort (low/high/max), and the signed-in HF OAuth token. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool | effort,history,image_path,message,system_prompt | Not stated |