Filesystem MCP Server (@shtse8/filesystem-mcp)

Created By
shtse8a year ago
Node.js Model Context Protocol (MCP) server providing secure, relative filesystem access for AI agents like Cline/Claude.
Overview

What is Filesystem MCP?

Filesystem MCP is a Node.js server that provides secure and relative filesystem access for AI agents like Cline and Claude, utilizing the Model Context Protocol (MCP).

How to use Filesystem MCP?

To use Filesystem MCP, you can deploy it via Docker, npx, or build it locally. For Docker, ensure your project directory is mounted to the container's /app directory.

Key features of Filesystem MCP?

  • Secure by Design: Operations are confined to the project root directory.
  • Comprehensive Toolset: Includes file listing, content manipulation, search and replace, directory management, deletion, and permissions management.
  • Modern Tech: Built with TypeScript and Node.js.
  • Input Validation: Uses Zod schemas for reliable argument validation.
  • Containerized: Available as a Docker image for easy deployment.

Use cases of Filesystem MCP?

  1. Empowering AI agents with controlled access to project files.
  2. Facilitating secure file operations in AI-driven applications.
  3. Managing project files efficiently within a defined directory structure.

FAQ from Filesystem MCP?

  • Can Filesystem MCP be used with any AI agent?

Yes! It is designed to work with AI agents like Cline and Claude.

  • Is there a Docker image available for Filesystem MCP?

Yes! It is available on Docker Hub for easy deployment.

  • How do I ensure security while using Filesystem MCP?

All operations are confined to the project root directory, preventing unauthorized access.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
shtse8
Star
3
Language
TypeScript
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago