File Operations MCP Server
Provides tools for common file processing operations including reading files, listing directories, searching across files, getting file info, and counting lines with built-in security features like path traversal protection.
README
File Operations MCP Server
A Model Context Protocol (MCP) server that provides tools for common file processing operations. Built with FastMCP and ready for deployment on Smithery.
Features
This server provides the following file operation tools:
- read_file: Read and return the contents of text files
- list_directory: List files and directories with optional glob pattern filtering
- search_in_files: Search for text across multiple files with pattern matching
- get_file_info: Get detailed information about files (size, type, permissions, etc.)
- count_lines: Count the number of lines in text files
Configuration
The server supports session-specific configuration:
- base_path: Base directory for file operations (default: current directory)
- max_file_size: Maximum file size in bytes to process (default: 1MB)
Security Features
- Path traversal protection (prevents accessing files outside base_path)
- File size limits to prevent memory issues
- Binary file detection and handling
- Error handling for permissions and encoding issues
Local Development
Prerequisites
- Python 3.12 or higher
uv(recommended),poetry, orpippackage manager
Setup
-
Install dependencies:
# Using uv (recommended) uv sync # Using poetry poetry install # Using pip pip install -e . -
Run the development server with interactive playground:
# Using uv uv run playground # Using poetry poetry run playground -
Or run the server without playground:
# Using uv uv run dev # Using poetry poetry run dev
The playground provides an interactive interface to test all server tools in real-time.
Deployment to Smithery
Prerequisites
- GitHub account
- Smithery account (connect at smithery.ai)
Steps
-
Initialize Git repository (if not already done):
cd fileops-server git init git add . git commit -m "Initial commit: File operations MCP server" -
Create GitHub repository:
- Go to github.com and create a new repository
- Follow GitHub's instructions to push your local repository:
git remote add origin https://github.com/YOUR_USERNAME/fileops-server.git git branch -M main git push -u origin main -
Connect to Smithery:
- Visit smithery.ai
- Connect your GitHub account
- Find your
fileops-serverrepository
-
Deploy:
- Navigate to the Deployments tab on your server page
- Click "Deploy" to build and host your server
- Smithery will automatically containerize and deploy your server
Post-Deployment
Once deployed, you can:
- Share your server with others
- Configure per-user settings (base_path, max_file_size)
- Monitor usage and logs through the Smithery dashboard
- Update the server by pushing changes to GitHub
Project Structure
fileops-server/
├── smithery.yaml # Smithery runtime configuration
├── pyproject.toml # Python project configuration
├── README.md # This file
└── src/
└── fileops_server/
├── __init__.py # Package initialization
└── server.py # MCP server implementation
Usage Examples
Read a File
# Tool: read_file
# Parameters: file_path="example.txt"
# Returns: Contents of example.txt
List Directory
# Tool: list_directory
# Parameters: directory_path=".", pattern="*.py"
# Returns: List of all Python files in the directory
Search in Files
# Tool: search_in_files
# Parameters: search_term="TODO", directory_path=".", file_pattern="*.py"
# Returns: All lines containing "TODO" in Python files
Get File Info
# Tool: get_file_info
# Parameters: file_path="example.txt"
# Returns: Detailed file information (size, type, permissions, etc.)
Count Lines
# Tool: count_lines
# Parameters: file_path="example.txt"
# Returns: Number of lines in the file
License
MIT License - feel free to use and modify as needed.
Contributing
Contributions are welcome! Please feel free to submit issues or pull requests.
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。