vision-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OCR_API_KEY | No | API key for the dedicated OCR endpoint. | |
| OCR_ENABLED | No | Set to 'true' to enable a dedicated OCR model. | |
| OCR_BASE_URL | No | Base URL for the dedicated OCR endpoint. | |
| OCR_MODEL_ID | No | Model ID for the dedicated OCR model. | |
| VISION_API_KEY | Yes | API key for the OpenAI-compatible vision endpoint. | |
| VISION_BASE_URL | Yes | Base URL of the OpenAI-compatible vision endpoint, e.g., https://your-provider.example/v1. | |
| VISION_MODEL_ID | Yes | Model ID for the vision model, e.g., glm-4v-flash. | |
| VISION_URL_MODE | No | Controls remote-image handling: 'auto' (default), 'passthrough', or 'download'. | |
| UV_DEFAULT_INDEX | No | PyPI index URL for package resolution (default: https://pypi.org/simple). | |
| VISION_ALLOWED_PATHS | No | Comma-separated list of allowed directories for local file access (e.g., /data,/tmp,/home/user/Pictures). |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| vision_analyzeA | Analyze an image using a vision-language model. Returns a unified JSON envelope wrapping summary, observations, uncertainties, and suggested follow-ups (see README 'Response format' for the full schema). Supports URL, local file path, data URL, and Base64 input. Task types guide the model:
|
| vision_inspectA | Inspect image metadata (dimensions, format, size, mode) without calling VLM. Use this before detailed analysis to understand the image dimensions and plan crop coordinates. |
| vision_crop_analyzeA | Crop a region of an image and analyze it with VLM. This is the most powerful tool for inspecting small text, UI elements, chart data, or error messages. Coordinates are NORMALIZED (0.0 to 1.0), where (0,0) is top-left and (1,1) is bottom-right. Workflow: Use vision_inspect first to get dimensions, then vision_analyze for overview, then vision_crop_analyze to zoom into specific regions of interest. |
| vision_extract_textA | Extract visible text from an image using OCR. Returns structured text organized by reading order. Use this for: screenshots with text, scanned documents, receipts, tables, forms, Chinese/English OCR, and any text-heavy images. Uses a configured dedicated OCR model when enabled. If the dedicated OCR model is unavailable, automatically falls back to the VLM provider. |
| vision_compareA | Compare two or more images and identify differences. Use for:
Returns structured differences with confidence levels. |
| vision_capabilitiesA | Return current vision-mcp server capabilities, supported models, and limits. Call this to discover what the server can do before using other 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 | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: general analysis, comparison, region analysis, OCR, and metadata inspection. There is no overlap in functionality.
All tool names follow the consistent pattern 'vision_<verb>' or 'vision_<verb>_<noun>', using lowercase and underscores. The naming is predictable and readable.
With 5 tools, the server is well-scoped for image analysis. Each tool addresses a core need without unnecessary clutter.
The tool set covers all essential image analysis operations: general analysis, comparison, region analysis, OCR, and metadata inspection. The vision_capabilities task type also provides self-description.