MCPInstall
mcp-url-parse-content logo

mcp-url-parse-content

by liujianqiao928 1 stars liujianqiao928/mcp-url-parse-content

MCP server for parsing PDF, PNG, JPG content into a model-friendly format.

View on GitHub
READMEmaster

服务介绍

这是一个用于解析pdf内容的mcp server，用于解析 pdf、png、jpg等格式，并整理成大模型所理解的格式输出。

开发环境

  • python 3.12
  • mcp sdk
  • uv
  • pypdf
  • paddle ocr

使用方法

{
    "mcpServers":{
        "urlParseContent":{
            "command": "uv",
            "args":[
                "--directory",
                "xxx/urlParseContent",
                "run",
                "main.py"
            ]
        }
    }
}

后续更新

  • 提高ocr识别
  • 增加 doc格式和Excel格式

More Web Scraping & Data Collection MCP servers

Similar servers from the same category.

BuiltWith

builtwith

Integrates with BuiltWith's technology detection API to identify and analyze web technologies used on specified domains, providing marketers and developers with comprehensive website stack information.

Web Scraping & Data Collection

ElfProxy Dynamic IP

elfproxy

Provides a bridge to ElfProxy's dynamic IP proxy service for retrieving country-specific proxy IPs, enabling IP rotation, geo-targeting, and bypassing regional restrictions.

WebOptimize

UniFuncs

unifuncs

Provides a bridge to the UniFuncs API for web search and web reading capabilities through TypeScript implementation with Express and NPX commands.

search

Bocha Search

bochaai

Integrates with Bocha, a Chinese search engine, to provide web search capabilities with rich structured data from billions of documents across multiple domains and languages.

search