A
licenseA
qualityF
maintenanceA multi-format MCP server that enables reading and generating Office, PDF, text, EPUB, and presentation documents. It provides unified tools for document processing and creation through AI assistants.
4
11
MIT
一个实现多种文档相关工具的 Python 包,用于转换和处理文档格式。这些工具通过 MCP server 接口暴露,以便与人工智能助手无缝集成。
# Create a virtual env and activate it
uv venv
source .venv/bin/activate
# Install the package in development mode
uv pip install -e .Related MCP server: Document Tools
# Start the MCP server
uv run main.py# Run all tests
uv run pytest工具被定义为 Python 函数,并注册到 MCP server 中:
mcp.tool()(my_function)工具描述应:
以一行摘要开头
提供功能的详细说明
说明何时使用(以及何时不使用)该工具
包含预期输入/输出的使用示例
使用 pydantic 中的 Field 进行参数描述:
from pydantic import Field
def my_tool(
param1: str = Field(description="Detailed description of this parameter"),
param2: int = Field(description="Explain what this parameter does")
) -> ReturnType:
"""Comprehensive docstring here"""
# ImplementationThis server cannot be deployed
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.