Filesystem MCP ServerSecure & Efficient Filesystem Access for AI Agents

Empower your AI agents (like Cline/Claude) with secure, efficient, and token-saving access to your project files via the Model Context Protocol.

🛡️ Secure by Design

All operations are strictly confined to the project root directory, preventing unauthorized access. Uses relative paths.

Batch operations minimize AI-server round trips, reducing token usage and latency compared to individual commands.

Offers a wide range of tools covering file/directory listing, reading, writing, editing, searching, moving, copying, and more.

Uses Zod for argument validation and provides detailed results for batch operations, indicating success or failure for each item.

Get started quickly using npx or Docker with minimal configuration in your MCP host environment.

MIT Licensed and open to contributions.