mcp-vision
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_MODEL | No | Model override for OpenAI | |
| MCP_OCR_MODEL | No | Model for custom provider | |
| OPENAI_API_KEY | No | API key for OpenAI | |
| ANTHROPIC_MODEL | No | Model override for Anthropic | |
| DASHSCOPE_MODEL | No | Model override for DashScope | |
| MCP_OCR_API_KEY | No | API key for custom provider | |
| MCP_OCR_BASE_URL | No | Base URL for custom provider | |
| MCP_OCR_PROVIDER | No | Provider selection (siliconflow, dashscope, volcengine, openai, anthropic, baidu_ocr, tencent_ocr, custom) | siliconflow |
| VOLCENGINE_MODEL | No | Model override for Volcengine | |
| ANTHROPIC_API_KEY | No | API key for Anthropic | |
| BAIDU_OCR_API_KEY | No | API key for Baidu OCR | |
| DASHSCOPE_API_KEY | No | API key for Alibaba DashScope | |
| SILICONFLOW_MODEL | No | Model override for Siliconflow | |
| TENCENT_SECRET_ID | No | Secret ID for Tencent OCR | |
| TENCENT_SECRET_KEY | No | Secret key for Tencent OCR | |
| VOLCENGINE_API_KEY | No | API key for Volcengine | |
| SILICONFLOW_API_KEY | No | API key for Siliconflow | |
| BAIDU_OCR_SECRET_KEY | No | Secret key for Baidu OCR |
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 | 分析图片内容。支持本地文件路径和远程 URL。可用于图像描述、视觉问答、图表分析等场景。 Args: image: 图片路径（本地绝对路径）或远程 URL prompt: 分析提示词，描述你希望如何分析这张图片。默认详细描述图片内容 |
| ocr_extractA | 从图片或 PDF 中提取文字（OCR）。适合识别截图、文档、代码中的文本内容。 Args: image: 图片或 PDF 文件路径（本地绝对路径）或远程 URL prompt: OCR 提示词。默认提取并格式化所有文字内容 |
| ocr_preciseA | 使用传统 OCR 引擎精准提取图片中的文字（返回结构化结果，含文字坐标和置信度）。 需要配置百度 OCR 或腾讯云 OCR 作为 Provider。 适合需要精确文字位置信息的场景（如发票、卡证、表格）。 Args: image: 图片文件路径（本地绝对路径）或远程 URL |
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
Most tools are distinct: analyze_image handles general analysis, while ocr_extract and ocr_precise both do OCR but differ in precision and output structure. However, an agent might confuse ocr_extract with ocr_precise since both extract text.
Two tools follow an 'ocr_' prefix pattern, while analyze_image uses a different verb_noun structure. The naming is mostly consistent within subgroups but lacks a unified pattern across all tools.
3 tools is slightly thin for a 'vision' server, but covers core analysis and OCR functions. The count is appropriate for a focused utility, though more tools could be beneficial.
Basic image analysis and OCR are covered, but missing common vision tasks like object detection or image manipulation. The toolset feels minimal for general vision needs, leaving notable gaps.