glm-vision-mcp
glm-vision-mcp
封装智谱 GLM-4.6V-Flash(免费视觉模型)的 MCP 服务器,向任意 MCP 客户端暴露一个 analyze_image 工具,支持单图/多图分析、OCR、多图对比。
特性
能力 | 说明 |
图片分析 | 本地路径 / http(s) URL / base64 data URI 均可,自动转 data URI |
多图对比 | 多张图片一次传入,按 prompt 对比分析 |
限流韧性 | 429 / 1302 / 1305 指数退避重试 → 多 Key 轮询 → 降级备用模型 |
配置自查 |
|
Related MCP server: vision-mcp
环境要求
Python >= 3.10
智谱开放平台 API Key(https://open.bigmodel.cn/usercenter/apikeys),
glm-4.6v-flash免费想进一步降低限流概率,可注册多个账号各取一个 Key,配置时用英文逗号分隔
安装
cd glm-vision-mcp
python -m venv .venv
.venv\Scripts\pip install -r requirements.txt启动
# stdio 模式(MCP 客户端默认方式)
$env:ZHIPU_API_KEY = "你的Key"
.venv\Scripts\python server.py
# SSE 调试模式(无鉴权,仅限本机)
.venv\Scripts\python server.py --sse 8090客户端配置
Codex(~/.codex/config.toml)
[mcp_servers.glm-vision]
command = "C:\\绝对路径\\glm-vision-mcp\\.venv\\Scripts\\python.exe"
args = ["C:\\绝对路径\\glm-vision-mcp\\server.py"]
[mcp_servers.glm-vision.env]
ZHIPU_API_KEY = "你的Key"
# GLM_VISION_MODELS = "glm-4.6v-flash"
# GLM_API_BASE = "https://open.bigmodel.cn/api/paas/v4/chat/completions"Claude Desktop(claude_desktop_config.json)
{
"mcpServers": {
"glm-vision": {
"command": "C:\\绝对路径\\glm-vision-mcp\\.venv\\Scripts\\python.exe",
"args": ["C:\\绝对路径\\glm-vision-mcp\\server.py"],
"env": { "ZHIPU_API_KEY": "你的Key" }
}
}
}工具接口
analyze_image(images, prompt, temperature, max_tokens, thinking)
参数 | 类型 | 必填 | 说明 |
| string[] | 是 | 本地路径 / http(s) URL / data URI |
| string | 否 | 分析要求,默认“请详细描述这张图片的内容” |
| number | 否 | 0.0~1.0,默认 0.7 |
| integer | 否 | 最大输出 token,默认 2048 |
| boolean | 否 | 深度思考模式,默认 false |
环境变量
变量 | 必填 | 说明 |
| 是 | 智谱 API Key,逗号分隔支持多 Key 轮询 |
| 否 | 模型优先级,逗号分隔,默认 |
| 否 | 覆盖 API 端点 |
注意事项
本地图片单张 ≤ 10MB,支持 jpg/jpeg/png/webp/gif/bmp
免费模型高峰期可能限流,全部 Key + 全部模型都限流时才报错,稍等 15~30 秒错峰重试
401/400 等非限流错误不降级不重试,直接返回,便于定位配置问题
验证
# 离线检查(不联网)
.venv\Scripts\python test_smoke.py
# 联网冒烟:MCP 握手 + analyze_image 真实调用
$env:ZHIPU_API_KEY = "你的Key"
.venv\Scripts\python test_smoke.py --liveAvailable Tools
2 toolsanalyze_imageA
调用智谱 GLM-4.6V-Flash 分析一张或多张图片。
适用:图片描述、OCR 文字提取、表格/图表解析、UI 截图理解、多图对比等。
Args: images: 图片列表,每项是本地文件路径、http(s):// URL 或 base64 data URI。 prompt: 对图片的提问或分析指令,如 “提取图中所有文字,保留排版顺序”。 temperature: 采样温度 0.0~1.0,越小越确定,默认 0.7。 max_tokens: 最大输出 token 数,默认 2048。 thinking: 是否开启深度思考(返回附带思考过程),默认 False。
Returns: dict,含 model / content(/ reasoning / elapsed_ms)字段;失败抛异常。
Inputs: images (required), prompt, thinking, max_tokens, +1 more.
check_configA
检查 MCP 配置是否就绪(不泄露 Key 本体)。
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools are completely distinct: analyze_image handles all image analysis tasks while check_config verifies setup. There is zero overlap or ambiguity in their purposes.
Both tools follow the consistent verb_noun snake_case convention—analyze_image and check_config. The pattern is clean and predictable, matching the higher-scoring examples.
With only 2 tools in a server, the count falls into the 'feels thin' category. While the core vision analysis capability is covered by a single tool, the overall server feels minimal and could reasonably be expected to have a few more supporting tools to feel substantial.
The single analysis tool fully covers the core domain of image description, OCR, and chart parsing—no obvious dead ends for standard usage. The config check provides useful operational support. Minor gaps like batch processing or model inquiry are absent but not critical for the stated scope.
Related MCP Connectors
MCP server for Qwen Image 3 AI image generation
MCP server exposing the YourImageShare upload API (upload/list/delete) as tools for AI agents.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Chat, image, video, and audio models from many vendors behind one remote MCP server and one key.
Related MCP Servers
- AlicenseAqualityCmaintenanceMulti-model vision understanding MCP server that provides unified image analysis for AI assistants without native vision, supporting models like GLM-4.6V, DeepSeek-OCR, Qwen3-VL-Flash, and more.1512 npm116MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for analyzing images using multiple vision LLM providers (OpenCode, OpenAI, Anthropic, Google, and custom OpenAI-compatible endpoints). Provides tools to analyze single or multiple images, list providers, and test vision capabilities.MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server that leverages Zhipu's free GLM-4.6V-Flash vision model to enable image, video, and file understanding (OCR, table parsing, defect detection, document Q&A, and more) across MCP-compatible clients like Codex and Claude Desktop.-
- FlicenseAqualityDmaintenanceA Model Context Protocol server that wraps the free GLM-4.6V-Flash vision model, enabling text-only LLM clients like Codex, Cursor, and Claude Desktop to analyze images, videos, and files (PDF/TXT) through standard MCP tools.32-