
MCP File Operations Server
A Model Context Protocol server that enables Claude Desktop to perform file operations like reading, writing, listing directories, and managing files through natural language commands.
README
MCP File Operations Server
A Model Context Protocol (MCP) server that provides file operation tools for Claude Desktop.
Features
- read_file: Read file contents
- write_file: Write content to files
- list_directory: List directory contents
- create_directory: Create directories
- delete_file: Delete files
- delete_directory: Delete directories
- copy_file: Copy files
- move_file: Move/rename files
- get_file_info: Get file metadata
Installation
Quick Installation
Run the installation script:
bash scripts/install.sh
Manual Installation
-
Create virtual environment:
python3 -m venv .venv source .venv/bin/activate
-
Install the package:
pip install -e .
-
Install development dependencies (optional):
pip install -e ".[dev]"
Testing
Run the test suite:
python -m pytest tests/
Or run tests directly:
python tests/test_file_operations.py
Claude Desktop Integration
-
Find your Claude Desktop config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
-
Add the server configuration:
{ "mcpServers": { "file-operations": { "command": "/bin/bash", "args": ["/path/to/your/mcp/scripts/run_server.sh"] } } }
Note: Update the path in
args
to match your actual installation directory. -
Restart Claude Desktop to load the new server.
Usage
Once integrated, you can use commands like:
- "Read the file at /path/to/file.txt"
- "Write 'Hello World' to /path/to/output.txt"
- "List the contents of /path/to/directory"
- "Create a directory at /path/to/new/dir"
- "Delete the file /path/to/unwanted.txt"
- "Copy file from /source to /destination"
Security Notes
- The server has full file system access
- Only use with trusted content
- Consider restricting paths in production environments
Testing
Run the test suite:
python test_server.py
LangGraph Integration
This package includes a complete LangGraph integration that allows you to use MCP file operations as tools within LangGraph workflows.
Installation with LangGraph
# Install with LangGraph support
pip install -e ".[langgraph]"
Quick Start
import asyncio
from mcp_file_operations.integrations.langgraph_client import create_mcp_file_tools
async def example():
# Create MCP file operation tools for LangGraph
file_tools = create_mcp_file_tools()
# Use tools in your LangGraph workflow
write_tool = next(tool for tool in file_tools if tool.name == "write_file")
result = await write_tool._arun(path="/tmp/test.txt", content="Hello LangGraph!")
print(result)
asyncio.run(example())
Examples
- Simple Integration:
examples/simple_langgraph_example.py
- Full Workflow:
examples/langgraph_file_workflow.py
- Documentation:
docs/LANGGRAPH_INTEGRATION.md
Available LangGraph Tools
All MCP file operations are available as LangGraph tools:
read_file
,write_file
,list_directory
,create_directory
delete_file
,delete_directory
,copy_file
,move_file
,get_file_info
License
MIT License
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。