vision-bridge-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_BRIDGE_CACHE | No | Set to '0' to disable cache. Default: '1' | 1 |
| VISION_BRIDGE_MODEL | No | Primary vision model name. Default: qwen-vl-max | qwen-vl-max |
| VISION_BRIDGE_MODELS | No | Comma-separated list of fallback models. | |
| VISION_BRIDGE_API_KEY | No | API key for the vision model backend. Required for remote services like DashScope or OpenAI. | |
| VISION_BRIDGE_BASE_URL | No | OpenAI compatible API base URL. Default: https://dashscope.aliyuncs.com/compatible-mode/v1 | https://dashscope.aliyuncs.com/compatible-mode/v1 |
| VISION_BRIDGE_MAX_TOKENS | No | Maximum output tokens for the vision model. Default: 4096 | 4096 |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| describe_imageC | REQUIRED when main model cannot see images (DeepSeek text, etc.). Converts image to detailed text via sidecar vision model with multi-model fallback. ## Image / Vision (required for text-only models like DeepSeek) Your base model CANNOT see images. When the user:
|
| extract_textA | OCR for screenshots/logs. Use when you need verbatim text from an image. |
| compare_imagesC | Compare before/after screenshots or UI states. Absorbed pattern from image_mcp. |
| vision_statusA | Show vision API config, model fallback chain, cache setting. |
| vision_rulesA | Returns markdown rules to paste into CLAUDE.md so the agent auto-calls vision tools. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |