What transport or protocol does tsuki_mcp_filesystem_server use?
It uses the JSON-RPC protocol over TCP/IP, listening on a configurable host and port.
@yuutotsuki
Basic information
A custom MCP-compatible server for searching local filesystem files. Works with OpenAI's Agent SDK via the resources/list method. ローカルファイルの検索を行う、自作のMCP対応サーバーです。 Agent SDK の `resources/list` に対応しています。
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"tsuki_mcp_filesystem_server": {
"command": "python",
"args": [
"main.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
tsuki_mcp_filesystem_server is a custom Model Context Protocol (MCP) server that provides file search and open operations over the local filesystem. It is designed for integration with OpenAI's Agent SDK, enabling AI agents to list and open local files via the resources/list method.
Clone the repository, install dependencies with pip install -r requirements.txt, copy .env.example to .env, configure the ROOT_PATH, HOST, PORT, and LOG_LEVEL settings, then start the server with python main.py. The server listens for MCP client requests on the configured host and port.
It uses the JSON-RPC protocol over TCP/IP, listening on a configurable host and port.
Python 3 and the packages listed in `requirements.txt` are required.
You must set the `ROOT_PATH` environment variable (or in `.env`) to specify the directory to be searched. Optionally, set `HOST`, `PORT`, and `LOG_LEVEL`.
The README states it is a custom, lightweight server focused on file search and open operations via the `resources/list` method.
The server only accesses files under the configured `ROOT_PATH` directory on the local filesystem. No external storage is used.
Go server implementing Model Context Protocol (MCP) for filesystem operations.
Official MCP server for pdfAssistant. Connect Claude, ChatGPT, or any MCP client to perform professional PDF processing like OCR, permanent redactions, secure encryption, format conversions, and 40+ advanced operations p

DeviceLink lets you share folders from your computer with AI assistants, securely and in real-time. Nothing is uploaded. Your files stay on your machine, and are only accessible while the device sharing them is connected
MCP server to extract contents from a PDF file
Comments