Filesystem MCP Server — Give AI Agents Safe Local File Access
Install the Filesystem MCP server to let Claude Code, Cursor, and Windsurf read, write, search, and navigate files on your local machine — with configurable directory boundaries so the AI only touches what you allow.
Install Filesystem MCP Server
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/Users/you/projects",
"/Users/you/Documents"
]
}
}
}Filesystem MCP — Local File Access for AI Agents
Official MCP server that gives AI agents safe, scoped access to your local filesystem. Read, write, search, and manage files and directories with configurable permissions. 4,000+ stars.
Jina Reader — AI-Friendly Web Content Extraction
Convert any URL to clean markdown for AI consumption. Free API at r.jina.ai strips ads, navigation, and clutter. Used by AI agents for web research and RAG.
Claude Code Templates — 600+ Agents, Commands & MCPs
Ready-to-use Claude Code configurations: 600+ agents, 200+ commands, 55+ MCPs, and project templates. Install any template with one command.
Google Stitch MCP — AI Design via Model Context Protocol
Connect Claude Code, Cursor, Gemini CLI, or VS Code to Google Stitch for AI-driven UI design. Create projects, generate screens from text, edit designs, manage design systems — all via MCP.
Pal MCP Server — Multi-Model AI Gateway for Claude Code
MCP server that lets Claude Code use Gemini, OpenAI, Grok, and Ollama as a unified AI dev team. Features model routing, CLI-to-CLI bridge, and conversation continuity across 7+ providers.
Chrome MCP Background Proxy — Fix Popups, Focus Stealing & Multi-Agent Conflicts
Drop-in proxy for Chrome MCP. Solves Chrome 146+ debugging popups, focus stealing, and multi-agent conflicts with persistent CDP connection, request ID remapping, and sessionId-based event routing.
Neon — Serverless Postgres with Database Branching
Serverless PostgreSQL with instant database branching, autoscaling, and a generous free tier. Branch your database like git branches — test schema changes without touching production. 16,000+ stars.
Appwrite — Open-Source Backend for AI Apps
Complete cloud backend with auth, database, storage, functions, and messaging in one platform. Self-hostable. 55K+ GitHub stars.
Neon MCP — Serverless Postgres via AI Agents
MCP server for Neon serverless Postgres. Create projects, branch databases, run SQL, optimize queries via natural language. Safe migration workflow with branching. MIT, 574+ stars.
Codebase Memory MCP — Code Knowledge Graph Server
High-performance MCP server that indexes codebases into persistent knowledge graphs. Supports 66 languages, sub-millisecond queries, and claims 99% fewer tokens than raw file context. 1,100+ stars.
Codebase Memory MCP — Code Intelligence for AI Agents
High-performance code intelligence MCP server. Indexes repos in milliseconds via tree-sitter AST, supports 66 languages, sub-ms graph queries. MIT, 1,300+ stars.
MCPHub — Centralized MCP Server Management Hub
Manage multiple MCP servers from one dashboard. Smart routing, hot-swap config, OAuth 2.0 auth. Deploy via Docker in one command. Apache-2.0, 2,000+ stars.
LMDeploy — High-Performance LLM Deployment Toolkit
Deploy and serve LLMs with 1.8x higher throughput than vLLM. 4-bit quantization, OpenAI-compatible API. By InternLM. 7.7K+ stars.
Smithery CLI — MCP Server Registry & Installer
Search, install, and manage MCP servers from Smithery's registry of 6,000+ servers. One command to connect any MCP server to Claude, Cursor, or other AI tools. AGPL-3.0.
Wrangler MCP — Cloudflare Workers for AI Agents
MCP server for managing Cloudflare Workers, KV, R2, and D1 from AI agents. Deploy serverless functions, manage storage, and query databases through Claude Code tool calls.
Docker MCP — Container Management for AI Agents
MCP server that gives AI agents Docker container management capabilities. Build, run, stop, and inspect containers through tool calls for automated DevOps workflows.
Firecrawl MCP — Web Scraping Server for AI Agents
Official Firecrawl MCP server for AI agents to scrape, crawl, and extract structured data from any website. Supports batch scraping, search, and markdown extraction. 15,000+ stars.
Haystack MCP — Connect AI Pipelines to MCP Clients
Expose Haystack RAG pipelines as MCP servers. Let Claude Code and other AI tools query your document search, QA, and retrieval pipelines through the MCP protocol.
Context7 — Live Library Docs for LLMs, 51K Stars
MCP server fetching up-to-date, version-specific library documentation into LLM context. Eliminates hallucinated APIs across 30+ AI coding tools.
MCP Inspector — Debug MCP Servers Visually
Official MCP Inspector for testing and debugging MCP servers. 9.3K+ stars. Web UI, tool/resource/prompt inspection, request testing.
Browser Use — AI Agent Browser Automation
Let AI agents control web browsers with natural language. Browser Use provides vision-based element detection, multi-tab support, and works with any LLM provider.
Unstructured — Document ETL for LLM Pipelines
Extract clean data from PDFs, DOCX, HTML, images, and emails for RAG and LLM ingestion. 14K+ GitHub stars.
Serena — Semantic Code Agent via MCP
Serena is a coding agent MCP server with semantic code retrieval and editing. 22K+ stars. Understands classes, functions, symbols for precise context-aware edits. MIT.
Uptime Kuma — Self-Hosted Uptime Monitoring
Monitor HTTP, TCP, DNS, Docker services with notifications to 90+ channels. Beautiful dashboard. 84K+ GitHub stars.
Context7 — Up-to-Date Docs MCP for AI Editors
MCP server that provides AI code editors with up-to-date library documentation. Eliminates hallucinations from outdated training data. Supports 1000+ libraries. 51K+ stars.
Glama — MCP Server Discovery and Management
Directory and management platform for MCP servers. Discover, install, and monitor Model Context Protocol servers for Claude Code, Cline, and other AI coding tools.
DBHub — Universal Database MCP Server, Zero Dependencies
Token-efficient database MCP server supporting Postgres, MySQL, MariaDB, SQL Server, and SQLite. Just two MCP tools, zero dependencies, read-only safe.
Chrome DevTools MCP — Browser Debugging for AI Agents
Give your AI coding agent full access to Chrome DevTools for browser automation, debugging, and performance analysis. Works with Claude, Cursor, Copilot, and 15+ AI tools.
PostgreSQL MCP Server — Database Queries for AI
MCP server for PostgreSQL database access. Run read-only SQL queries, inspect schemas, list tables, and analyze data directly from Claude Code or Cursor.
mcp-agent — Build AI Agents with MCP Patterns
mcp-agent is a Python framework for building AI agents using the Model Context Protocol. 8.2K+ GitHub stars. Implements composable workflow patterns (orchestrator, map-reduce, evaluator-optimizer, rou
The foundation of every local AI workflow
The Filesystem MCP server is the most fundamental MCP integration — and often the first one developers install. It gives your AI agent the ability to read files, write files, create directories, list contents, search by name, and move or copy files. Unlike the file access built into Claude Code's native tool, MCP filesystem access is boundary-scoped: you specify exactly which directories the server can see, and it cannot escape those boundaries.
This architecture is critical for security. If you point the Filesystem MCP server at /Users/you/projects, it can read and write anything under that path — but it cannot access ~/.ssh, ~/.aws, or any other directory outside the boundary. For teams working with sensitive codebases alongside personal files, this is the difference between usable AI and unacceptable risk.
The server pairs naturally with every other MCP integration. Need your AI to read a local config file and use it to set up a PostgreSQL connection? Filesystem + Postgres. Need it to read a design spec PDF and commit code to GitHub? Filesystem + GitHub. For self-hosted AI setups, the filesystem server enables local document processing and RAG pipelines without sending any files to external services.
An AI that can't read your files is an AI that can't understand your project. The Filesystem MCP server fixes that — safely.
Questions fréquentes
What is the Filesystem MCP server?+
The Filesystem MCP server is an official reference implementation from the Model Context Protocol project. It exposes local file operations — read, write, create, delete, move, search, list — as MCP tools. You specify allowed directories at startup, and the server enforces those boundaries. It runs locally and never sends file data to external services.
Is it safe to give AI access to my filesystem?+
Yes, with proper scoping. The server only accesses directories you explicitly list as arguments. It cannot traverse above those paths — /Users/you/projects cannot reach /Users/you/.ssh. Best practices: (1) Never include your home directory root. (2) Exclude directories with secrets (.env files, credentials). (3) Start with read access to your project folders only.
How does this differ from Claude Code's built-in file access?+
Claude Code has native file read/write tools that work within the current working directory. The Filesystem MCP server adds capabilities beyond the CWD: cross-project file access, file search by name patterns, directory tree listing, and explicit boundary control. It's most useful when your agent needs to reference files across multiple projects or access files outside the current repo.
Can I restrict the server to read-only access?+
The reference implementation does not have a built-in read-only flag, but you can achieve this through OS-level permissions: run the server as a user that only has read access to the target directories. Alternatively, some community forks add a --read-only flag. For production setups, OS permissions are the safest approach.