tsuki_mcp_filesystem_server MCP Server

What does “tsuki_mcp_filesystem_server” MCP Server do?

The tsuki_mcp_filesystem_server is a custom server compatible with the Model Context Protocol (MCP) designed to facilitate searching and opening files on the local filesystem. Tailored for integration with OpenAI’s Agent SDK, it exposes file system resources via the MCP, enabling AI assistants and agents to query, list, and access files within a specified directory on the host machine. Key features include automatic MIME type detection and flexible configuration through environment variables. By supporting the resources/list method, this server enables development workflows that require programmatic file discovery or management, allowing AI-powered tools to interact with local files in a standardized and secure manner.

List of Prompts

No prompt templates are mentioned in the repository.

List of Resources

• File System Resource
  Provides access to local filesystem files, allowing clients to search and list files within a specified directory.
• resources/list
  An endpoint that retrieves a list of files in the target directory, exposing them as resources for AI clients.

List of Tools

• resources/list
  Tool that allows listing files in the configured local directory, making them available to clients for further actions.

Use Cases of this MCP Server

• Local File Discovery
  Developers can use the server to programmatically discover and list files within a target directory, aiding in file management tasks.
• File Context for LLMs
  Enables large language models and AI agents to retrieve local file listings, which can be used as context for code analysis or documentation tasks.
• Agent SDK Integration
  Works seamlessly with OpenAI’s Agent SDK, allowing agents to use file search capabilities as part of broader automation flows.
• Automated MIME Type Detection
  Automatically detects MIME types for files, which is useful when processing or filtering files based on type.

How to set it up

Windsurf

1. Prerequisites:
   Ensure Python and pip are installed.
2. Clone the repository:
   git clone https://github.com/yuutotsuki/tsuki_mcp_filesystem_server.git
3. Install dependencies:
   pip install -r requirements.txt
4. Configure environment:
   Copy .env.example to .env and edit ROOT_PATH, HOST, PORT, and LOG_LEVEL.
5. Register with Windsurf:
   Add the server info to your Windsurf MCP configuration.

Example JSON:

{
  "mcpServers": {
    "tsuki_mcp_filesystem": {
      "command": "python",
      "args": ["main.py"]
    }
  }
}

Securing API Keys:

{
  "env": {
    "ROOT_PATH": "/path/to/your/search/directory"
  },
  "inputs": {}
}

Claude

1. Prerequisites:
   Install Python and dependencies as above.
2. Set up environment:
   Configure .env with your directory.
3. Integrate with Claude:
   Add MCP server configuration to your Claude settings.
4. Start the server:
   python main.py
5. Verify connection:
   Ensure Claude can see the MCP server.

Example JSON:

{
  "mcpServers": {
    "tsuki_mcp_filesystem": {
      "command": "python",
      "args": ["main.py"]
    }
  }
}

Securing API Keys:

{
  "env": {
    "ROOT_PATH": "/path/to/your/search/directory"
  },
  "inputs": {}
}

Cursor

1. Clone and install:
   Clone the repo and install requirements.
2. Set up environment:
   Copy and edit .env.
3. Configure Cursor:
   Add the MCP server to Cursor’s configuration.
4. Run the server:
   python main.py
5. Restart Cursor and check:
   Confirm MCP is recognized.

Example JSON:

{
  "mcpServers": {
    "tsuki_mcp_filesystem": {
      "command": "python",
      "args": ["main.py"]
    }
  }
}

Securing API Keys:

{
  "env": {
    "ROOT_PATH": "/path/to/your/search/directory"
  },
  "inputs": {}
}

Cline

1. Install requirements:
   As above.
2. Configure .env:
   Set ROOT_PATH, HOST, and PORT.
3. Add to Cline:
   Register the MCP server in Cline’s config.
4. Start the server:
   python main.py
5. Check operation:
   Validate MCP server visibility.

Example JSON:

{
  "mcpServers": {
    "tsuki_mcp_filesystem": {
      "command": "python",
      "args": ["main.py"]
    }
  }
}

Securing API Keys:

{
  "env": {
    "ROOT_PATH": "/path/to/your/search/directory"
  },
  "inputs": {}
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "tsuki_mcp_filesystem": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “tsuki_mcp_filesystem” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the information present, tsuki_mcp_filesystem_server is a minimal yet focused MCP server for local filesystem search. It provides essential features and offers clear configuration, but lacks advanced MCP primitives like prompts, roots, or sampling support. Its utility is high for specialized use cases, but broader applications would require more functionality.

MCP Score