MCPFileSystem_Client

What is MCPFileSystem_Client?

MCPFileSystem_Client is a client application that connects a local LLM (compatible with the OpenAI SDK) to the MCP filesystem server, allowing the model to read and write files in specified directories. It is intended for developers who want to give an LLM controlled access to the local file system.

How to use MCPFileSystem_Client?

1. Start a local LLM that supports the OpenAI SDK (e.g., Jan).
2. Edit the .env file to set the model name, system prompt, and server base URL (defaults are provided).
3. Run node app.js.

Key features of MCPFileSystem_Client

• Connects an OpenAI‑compatible LLM to the filesystem via MCP.
• Restricts file access to directories specified in app.js.
• Uses StdioClientTransport with the official MCP filesystem server.
• Configured via environment variables (model, prompt, base URL).
• Requires a model that supports tool/function calling.

Use cases of MCPFileSystem_Client

• Let an LLM read files from a local project directory.
• Allow an LLM to write output files (e.g., generated code or reports).
• Provide controlled file access to an LLM running on a local server.

FAQ from MCPFileSystem_Client

Which directories can the LLM access?

Only the directories listed in the args array inside app.js (by default a folder named files). You can add or change paths there.

What models does MCPFileSystem_Client work with?

It works with any model that is compatible with the OpenAI SDK and supports tool/function calling. The default model in .env example may not work; you must use a model with tool‑calling capability.

How do I change the LLM endpoint?

Modify the BASE_URL environment variable in .env. A default value is already provided.

Does MCPFileSystem_Client run on a remote machine?

No, it launches the MCP filesystem server locally via npx and communicates over stdio. The host machine’s file system is used.