open-vision-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Reserved, not used by stdio transport. | 3000 |
| MODEL | No | Model ID. Required for together, deepinfra, fireworks, chutes; ignored by azure; optional otherwise. | |
| API_KEY | Yes | API key for the selected provider. Required. | |
| BASE_URL | No | Full base URL including /v1 or similar. Required for azure; optional for others (has per-provider default). | |
| PROVIDER | No | Provider discriminator (openrouter, openai, together, deepinfra, fireworks, groq, chutes, cerebras, azure, ollama). | openrouter |
| LOG_LEVEL | No | Log level: debug, info, warn, error. | info |
| EXTRA_HEADERS | No | JSON object string of extra HTTP headers. | |
| MAX_IMAGE_SIZE | No | Maximum image size in bytes. | 10485760 |
| RETRY_ATTEMPTS | No | Reserved, not yet implemented. | 3 |
| OPENROUTER_MODEL | No | Legacy model for OpenRouter, maps to MODEL. | |
| OPENROUTER_API_KEY | No | Legacy API key for OpenRouter, maps to API_KEY. | |
| OPENROUTER_BASE_URL | No | Legacy base URL for OpenRouter, maps to BASE_URL. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_imageB | Analyze images using the configured vision provider. Supports various input formats including base64, file paths, and URLs. |
| analyze_webpage_screenshotB | Specialized tool for analyzing webpage screenshots. Extracts content, layout information, and interactive elements from web pages. |
| analyze_mobile_app_screenshotA | Specialized tool for analyzing mobile app screenshots. Provides insights into UI design, user experience, platform conventions, and app functionality. |
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 3 tools
Tools are mostly distinct: analyze_image is generic, while analyze_mobile_app_screenshot and analyze_webpage_screenshot target specific domains. However, an agent could potentially use analyze_image for screenshots, causing some overlap.
All tool names follow a consistent 'analyze_<noun>' pattern, making them predictable and easy to understand.
Three tools is a reasonable number for a focused vision analysis server. It is slightly on the lower end but not overly sparse, covering both general and specialized analysis.
The tool set covers basic image analysis and two common screenshot types. Missing operations like object detection or text extraction for general images are notable gaps, but the core analysis use case is addressed.