vision-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_MODEL | Yes | 支持图片输入的模型 | |
| VISION_API_KEY | Yes | API Key | |
| VISION_TIMEOUT | No | 调用超时秒数，默认 `120` | 120 |
| VISION_BASE_URL | Yes | Provider 地址 |
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 |
|---|---|
| analyze_imageA | DO NOT CALL if you natively support vision and can access the supplied image directly. Call this MCP only when native vision is unavailable, the image source is inaccessible to your native vision capability, or the user explicitly requests this MCP or its configured provider. Analyze one local image path, HTTP(S) image URL, or image data URL. This CLI-friendly single-image tool is the simplest entry point for mcporter and shell automation. Use understand_image for multiple images. |
| understand_imageA | DO NOT CALL if you natively support vision and can access the supplied image directly. Call this MCP only when native vision is unavailable, the image source is inaccessible to your native vision capability, or the user explicitly requests this MCP or its configured provider. Understand one or more images for description, OCR, document extraction, UI inspection, chart reading, comparison, spatial reasoning, or code/error screenshot analysis. Inputs may be local paths, HTTP(S) URLs, or image data URLs. Built-in prompt modes and optional ASCII rendering are available. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| quickstart | Required configuration, source startup, Inspector, and tool selection. |
| configuration | Environment variables, endpoint selection, and secret handling. |
| tools | Tool selection, image inputs, prompt modes, and ASCII behavior. |
| mcporter | Configure, discover, and call this MCP with mcporter. |
| uvx | Run from source, PyPI, or an unpublished Git repository. |
TDQS
Scored across 2 tools
Both tools analyze images, but analyze_image is for a single image while understand_image supports multiple images and more modes. The descriptions include cross-references, which helps, but the strong overlap in purpose could still confuse an agent.
Both tool names follow the same verb_noun pattern (analyze_image, understand_image) and are grammatically consistent, making the naming predictable.
With only two tools, the server feels thin for a vision MCP, though it covers both single-image and multi-image analysis. It is borderline but not severely under-scoped.
The two tools cover a broad range of vision tasks (description, OCR, document extraction, UI inspection, chart reading, etc.), leaving only minor gaps such as direct image metadata retrieval or manipulation.