Skip to main content

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 glm-4.1v-thinking-flash
配置自查 check_config 工具检查 Key/模型/端点,不泄露 Key

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
images string[] 本地路径 / http(s) URL / data URI
prompt string 分析要求,默认“请详细描述这张图片的内容”
temperature number 0.0~1.0,默认 0.7
max_tokens integer 最大输出 token,默认 2048
thinking boolean 深度思考模式,默认 false

环境变量

变量 必填 说明
ZHIPU_API_KEY 智谱 API Key,逗号分隔支持多 Key 轮询
GLM_VISION_MODELS 模型优先级,逗号分隔,默认 glm-4.6v-flash,glm-4.1v-thinking-flash
GLM_API_BASE 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 --live

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

glm_vision_mcp_river831-1.0.0.tar.gz (9.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

glm_vision_mcp_river831-1.0.0-py3-none-any.whl (9.0 kB view details)

Uploaded Python 3

File details

Details for the file glm_vision_mcp_river831-1.0.0.tar.gz.

File metadata

  • Download URL: glm_vision_mcp_river831-1.0.0.tar.gz
  • Upload date:
  • Size: 9.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.14.6

File hashes

Hashes for glm_vision_mcp_river831-1.0.0.tar.gz
Algorithm Hash digest
SHA256 5144d9b37e0c3eefc0063b4b5f4c8cb4b3264f4bb7372e567c7a4319ee404978
MD5 8e2c5b19cddb98c998904601134536c1
BLAKE2b-256 2e4d2031476579850816232b58f97cc9fd230cbdbde58def4ed65b553cf12db6

See more details on using hashes here.

File details

Details for the file glm_vision_mcp_river831-1.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for glm_vision_mcp_river831-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b08e07a294660fcb2ef6e7bcd777b268fa22c18541cedc8953617fa5d87e6e75
MD5 e1ed3c50fec6df04286c224755b2e191
BLAKE2b-256 ab42977e25c61a502a1484941cce1c39c73e060e0ed9cc5a9dd0c963418e33a4

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page