mcp-six-eyes
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_MODEL | No | Vision model to use. Defaults per provider, but required for custom provider. | |
| GOOGLE_API_KEY | No | Google Gemini API key. Required when VISION_PROVIDER is 'google'. | |
| OPENAI_API_KEY | No | OpenAI API key. Required when VISION_PROVIDER is 'openai'. | |
| VISION_API_KEY | No | API key for custom OpenAI-compatible endpoint. Required when VISION_PROVIDER is 'custom'. | |
| VISION_BASE_URL | No | Base URL for custom OpenAI-compatible endpoint. Required when VISION_PROVIDER is 'custom'. | |
| VISION_PROVIDER | No | The vision provider to use. One of openai, anthropic, google, openrouter, custom. Must be set. | |
| ANTHROPIC_API_KEY | No | Anthropic API key. Required when VISION_PROVIDER is 'anthropic'. | |
| VISION_MAX_IMAGES | No | Maximum number of images per call. Default is 10. | 10 |
| OPENROUTER_API_KEY | No | OpenRouter API key. Required when VISION_PROVIDER is 'openrouter'. | |
| VISION_MAX_IMAGE_BYTES | No | Maximum image size in bytes. Default is 20971520. | 20971520 |
| VISION_FALLBACK_PROVIDER | No | Optional fallback provider. One of openai, anthropic, google, openrouter, custom. |
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 |
|---|---|
| analyze_imageA | Analyze one or more images with a vision model and return plain text. Use for general Q&A when the host model cannot see images. Supports single |
| describe_imageA | Produce a detailed textual description of one or more images so a text-only model can reason about them. Prefer for general scene/UI understanding and multi-upload context dumps. |
| ocr_imageA | Extract readable text from one or more images (screenshots, documents, diagrams, error dialogs). Multi-image calls return a section per image label. |
| compare_imagesA | Compare two or more images and explain similarities/differences. Use for "compare image 1 and 2", before/after, A/B UI, design variants, or sequential screenshots. |
| refer_imagesA | Answer a question that refers to specific uploads by label ("refer image 1 and 2", "only the second screenshot", "both figures"). Grounds every claim in image labels. |
| inspect_uiA | Inspect UI screenshots: layout, components, states, copy, errors, and likely UX/accessibility issues. Accepts one screen or a multi-step flow. |
| read_chartA | Read charts, graphs, plots, tables, and dashboards. Extracts axes, series, trends, and key values (marks estimates when exact pixels are unclear). |
| explain_diagramA | Explain architecture diagrams, flowcharts, sequence diagrams, ERDs, UML, whiteboards, and similar figures for a text-only agent. |
| extract_from_imagesA | Extract structured data (JSON) from one or more images: forms, receipts, IDs, tables, invoices, labels. Optional schema steers field names. |
| vision_statusA | Show which vision provider/model this MCP server is configured to use, plus image limits. |
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 10 tools
Most tools have clearly distinct purposes: general Q&A, description, OCR, comparison, UI inspection, chart reading, diagram explanation, and structured extraction. Some overlap exists between analyze_image, describe_image, and refer_images, but their descriptions clarify the intended use cases, so agent confusion is unlikely.
The naming convention is largely verb_noun (analyze_image, compare_images, inspect_ui, read_chart, explain_diagram, extract_from_images). Minor deviations include vision_status (noun_noun) and ocr_image (acronym as verb), but the pattern is readable and predictable overall.
With 10 tools, the server is well-scoped for an image analysis domain. Each tool addresses a distinct need, and the count is within the ideal 3-15 range for a focused MCP server.
The tool surface covers general image Q&A, detailed description, OCR, comparison, labeled references, UI inspection, chart reading, diagram explanation, and structured data extraction—no obvious dead ends or missing essential operations for an image understanding server.