web-perception-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NANOGPT_MODEL | No | Vision model to use | minimax/minimax-m3 |
| MAX_TEXT_LENGTH | No | Max characters in extracted text | 50000 |
| NANOGPT_API_KEY | Yes | Your nanoGPT API key | |
| NANOGPT_BASE_URL | No | API endpoint. Use /api/v1 for pay-as-you-go. | https://nano-gpt.com/api/subscription/v1 |
| NANOGPT_MAX_TOKENS | No | Default max tokens | 2000 |
| REQUEST_TIMEOUT_MS | No | HTTP request timeout | 30000 |
| NANOGPT_TEMPERATURE | No | Default temperature | 0.3 |
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 |
|---|---|
| inspect_pageA | Inspect a webpage's structure, metadata, and content. Use for understanding what's on a page without visual analysis. Basic mode uses static fetch (fast, no browser). Full mode uses headless browser for DOM/accessibility/element extraction. Does NOT invoke the vision model. |
| analyze_imageA | Analyze one or more local image files using MiniMax vision. No browser involved. Use for screenshots, mockups, design files, or any image. Supports PNG, JPEG, GIF, WebP, BMP. |
| analyze_page_visualA | Analyze a webpage visually using screenshot + DOM structure + MiniMax vision. Use for design critique, UX review, visual hierarchy, layout analysis, UI bugs, and above-the-fold analysis. Defaults to viewport screenshot. Returns structured findings with element refs and evidence. |
| extract_page_dataA | Extract structured data from a webpage matching a provided schema. DOM-first: uses static extraction first, escalates to headless browser then MiniMax vision only if needed. Use for pricing tiers, product info, contact details, speaker lists, tables, API docs, or any structured content. |
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 4 tools
Each tool has a clearly distinct scope: local image analysis, webpage visual analysis, structured data extraction, and page structure inspection. No overlaps or ambiguities.
All tool names follow a consistent verb_noun pattern (analyze_image, analyze_page_visual, extract_page_data, inspect_page), making it easy to predict functionality.
With 4 tools, the set is well-scoped for web perception tasks—neither too sparse nor too bloated, covering the essential operations.
Covers all core aspects: image analysis, webpage visual analysis, structured data extraction, and page structure inspection. No obvious gaps for the domain.