MCP Filesystem Server

Created By
Spark-Lianga year ago
Overview

What is MCP Filesystem Server?

MCP Filesystem Server is a file system server based on the Model Context Protocol (MCP), implemented using Python and FastMCP.

How to use MCP Filesystem Server?

To use the MCP Filesystem Server, you can start it in different modes (stdio, HTTP, SSE) and specify allowed directories for access. For example, run mcp-filesystem-server for stdio mode or mcp-filesystem-server http --port 8080 --allowed-dir /home/user for HTTP mode.

Key features of MCP Filesystem Server?

  • Secure access control allowing access only to specified directories.
  • Complete file operations including read, write, create, move, and search.
  • A rich set of tools provided through the MCP protocol.
  • Resource management for files, directories, and configuration resources.
  • Multiple startup modes including stdio, HTTP, and SSE.
  • Test-driven development with complete test coverage.

Use cases of MCP Filesystem Server?

  1. Integrating with web applications for file management.
  2. Real-time communication applications using SSE.
  3. Command-line tools for file operations in a secure environment.

FAQ from MCP Filesystem Server?

  • Is MCP Filesystem Server secure?

Yes! It has features like path restrictions and permission checks to ensure secure access.

  • What programming language is used?

The server is implemented in Python.

  • Can I contribute to the project?

Yes! Contributions are welcome, and guidelines are provided in the repository.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Spark-Liang
Star
0
Language
Python
License
-
Category
file-systems
Tags

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