MCP File Operations Agent

Name: MCP File Operations Agent
Author: dynstat

@dynstat

代码仓库

关于 MCP File Operations Agent

A working example of your own agents from the scratch and using it with the mcp servers from scratch

#mcp #agents #mcp-server #mcp-client

基本信息

分类

AI 与智能体

运行时

python

传输方式

stdio

发布者

dynstat

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "File Operations Agent": {
      "command": "python",
      "args": [
        "file_agent_server.py"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP File Operations Agent?

MCP File Operations Agent is a simple Model Context Protocol (MCP) server that exposes file system operations as tools, enabling AI agents to read file contents, write to files, and list directory contents through a client-server architecture. It is built for developers integrating file manipulation into MCP-based workflows.

How to use MCP File Operations Agent?

Install the package with pip install -e ., then create a .env file with your API keys. Run the server with python file_agent_server.py and the client with python file_agent_client.py. The server supports both Stdio and SSE transports; see the provided code examples for tool definition and client connection.

Key features of MCP File Operations Agent

Read file contents and return them as text.
Write content to specified files.
List directory contents.
Supports Stdio and SSE transport layers.
Includes a client that integrates with Google's Gemini API.

Use cases of MCP File Operations Agent

Allow a Gemini-based agent to read configuration or log files.
Enable an MCP client to write generated content to disk.
Provide an AI assistant with the ability to browse project directories.
Integrate file operations into Cursor IDE via the .cursor/mcp.json configuration.

FAQ from MCP File Operations Agent

What dependencies are required?

Python 3.12 or higher, and the packages mcp[cli]>=1.6.0, google-genai>=1.12.1, and python-dotenv.

How do I configure API keys?

Create a .env file in the project root with your API keys, following the format shown in .env-sample.

What file operations are available?

The server provides three tools: read_file to read a file, write_file to write content to a file, and a tool to list directory contents (not explicitly named but implied by features).

How does transport work?

The server can run via Stdio (local inter-process communication) or SSE (HTTP-based, suitable for network interactions). Both are demonstrated with complete code examples in the README.