GLM-4.5V MCP Server

GLM-4.5V MCP Server

Enables multimodal AI capabilities through GLM-4.5V API for image processing, visual querying with OCR/QA/detection modes, and file content extraction from various formats including PDFs, documents, and images.

Category
Visit Server

README

GLM-4.5V MCP Server

GLM-4.5V 多模态能力的 MCP 服务器，提供图像处理、视觉查询和文件处理功能。

功能

  • read_image: 读取本地/URL图片并返回 dataURL 与尺寸信息
  • vision_query: 调用 GLM-4.5V 对图片进行 OCR/问答/检测
  • process_file: 使用 GLM-4.5V 处理文件（上传并提取内容）

安装

npm install

配置

复制环境变量文件：

cp .env.example .env

编辑 .env 文件，填入你的 GLM API Key：

GLM_API_KEY=your_api_key_here
GLM_BASE_URL=https://open.bigmodel.cn/api/paas/v4/chat/completions

构建

npm run build

运行

npm start

或使用启动脚本：

./start-mcp.sh

开发模式

npm run dev

测试功能

创建测试文件并验证功能：

node scripts/test-file-processing.js

工具说明

read_image

读取图片并返回 base64 编码的 dataURL。

参数：

  • path (必需): 图片路径或URL
  • maxSide (可选): 最大边长，用于缩放

vision_query

使用 GLM-4.5V 分析图片。

参数：

  • path (必需): 图片路径或URL
  • prompt (必需): 查询提示词
  • mode (可选): 查询模式 ("describe", "ocr", "qa", "detect")
  • returnJson (可选): 是否返回JSON格式结果

process_file

使用 GLM-4.5V 处理文件，支持多种格式的文件上传和内容提取。

支持的文件格式：

  • 文档：PDF、DOCX、DOC、XLS、XLSX、PPT、PPTX、CSV、TXT
  • 图片：PNG、JPG、JPEG

文件大小限制：

  • 图片文件：最大 5MB
  • 其他文件：最大 50MB

参数：

  • filePath (必需): 本地文件路径
  • extractPrompt (可选): 内容提取提示词，用于指导如何提取文件内容

返回结果：

{
  "ok": true,
  "fileId": "file-xxx",
  "content": "提取的文件内容...",
  "fileType": "PDF文档",
  "filename": "document.pdf",
  "metadata": {
    "uploadTime": 1234567890,
    "fileSize": 1024000,
    "processingTime": 5000
  }
}

使用示例

处理 PDF 文档

# 通过 MCP 调用
{
  "tool": "process_file",
  "arguments": {
    "filePath": "./documents/report.pdf",
    "extractPrompt": "请提取文档中的主要内容和关键信息"
  }
}

处理 Excel 表格

{
  "tool": "process_file",
  "arguments": {
    "filePath": "./data/sales.xlsx",
    "extractPrompt": "请分析表格数据并总结销售趋势"
  }
}

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured