Document Organizer MCP
Enables agents to manage and organize local documents by listing, inspecting, extracting text, searching, and renaming files, with optional Google Drive integration.
README
Workspace MCP Server
A minimal Python MCP server built with the official MCP Python SDK and prepared for deployment on Render from GitHub.
Files
server.py: the MCP server entrypointrequirements.txt: Python dependenciesrender.yaml: Render deployment blueprint
What this server does
This starter server exposes:
echo: returns the text you send itadd_numbers: adds two numberslist_workspace_files: lists files inside the app directoryread_text_file: reads a UTF-8 text fileread_json_file: reads and parses a JSON file
It also exposes a resource at workspace://server-info.
Run locally
-
Install dependencies:
pip install -r requirements.txt -
Run in local stdio mode:
python server.py -
Run in MCP dev mode:
uv run mcp dev server.py -
Run in HTTP mode locally:
MCP_TRANSPORT=streamable-http python server.py
By default, local HTTP mode listens on 127.0.0.1:8000, and the MCP endpoint is:
http://127.0.0.1:8000/mcp
Deploy on Render
Option 1: Use render.yaml
- Push these files to your GitHub repository.
- In Render, create a new Blueprint service from that repository.
- Render will read
render.yamland create the web service automatically.
Option 2: Manual Web Service setup
If you do not want to use the blueprint file, create a Render Web Service with:
-
Build Command:
pip install -r requirements.txt -
Start Command:
python server.py -
Environment Variable:
MCP_TRANSPORT=streamable-http
Render endpoint
After deployment, the MCP HTTP endpoint is:
https://YOUR-RENDER-SERVICE.onrender.com/mcp
Render supplies the PORT environment variable automatically. This server is already set up to bind to that port and to host 0.0.0.0 when running on Render.
Notes
stdiomode is for local MCP usage, not for Render web deployment.streamable-httpmode is the correct mode for Render.- If you rename the service, you do not need to change the code.
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。