Schema | vision-bridge-mcp

vision-bridge-mcp

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

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": true }

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: attaches or references an image path pastes a screenshot you see `[Unsupported
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.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/G12789/vision-bridge-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server