Word MCP Server
Enables creation and management of Word documents from markdown content, with support for multiple templates and conversion of chat conversations to formatted Word documents.
README
Word MCP Server
A FastAPI-based Word document generation server with full MCP (Model Context Protocol) support.
Features
- REST API for document creation and management
- MCP Protocol Support for integration with MCP-compatible clients
- Markdown Support in documents
- Multiple Templates (standard, report, memo, letter)
- Chat Export functionality to convert conversations to Word documents
- Health Check endpoint for monitoring
API Endpoints
Health Check
GET /health- Service health status
Document Operations
POST /word/create- Create a new Word documentPOST /word/create-from-chat- Create a document from chat messagesGET /word/list- List all documentsGET /word/download/{filename}- Download a documentDELETE /word/delete/{filename}- Delete a document
MCP Protocol
POST /mcp- MCP JSON-RPC 2.0 endpoint
Service Info
GET /- Root endpoint with service informationGET /tools- Get available tools
Deployment
Docker Compose
cd word-mcp-server
docker-compose build
docker-compose up -d
The service will be available at https://word.mac.mndambuki.me.ke via Traefik.
Local Development
pip install -r requirements.txt
python server.py
The server will run on http://localhost:8004
MCP Protocol Support
The server implements the MCP JSON-RPC 2.0 protocol with the following methods:
initialize- Initialize the MCP connectiontools/list- List available toolstools/call- Call a toolresources/list- List available resourcesresources/read- Read a resource
Example Requests
Create a Document (REST)
curl -X POST http://localhost:8004/word/create \
-H "Content-Type: application/json" \
-d '{
"title": "My Document",
"content": "# Heading\n\nThis is a paragraph.",
"author": "John Doe",
"template": "standard"
}'
Create a Document (MCP Protocol)
curl -X POST http://localhost:8004/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "create_document",
"arguments": {
"title": "My Document",
"content": "# Heading\n\nThis is a paragraph."
}
},
"id": 1
}'
Environment Variables
TZ- Timezone (default: Africa/Nairobi)PORT- Server port (default: 8004)
Requirements
- Python 3.11+
- Docker (for containerized deployment)
- External Traefik network (for Docker Compose)
Configuration
Documents are stored in /app/documents inside the container. In Docker Compose, this can be mounted to a local directory.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。