Filesystem
OfficialProvides secure filesystem operations for AI agents with batch processing to read, write, and search files while staying confined to your project directory.
Read, write, and manipulate local files through a controlled API.
What it does
- Read and write files in batch operations
- Search file contents with pattern matching
- List directory contents recursively
- Create and delete files safely
- Validate file paths within project boundaries
- Process multiple files in single requests
Best for
About Filesystem
Filesystem is an official MCP server published by anthropic that provides AI assistants with tools and capabilities via the Model Context Protocol. Learn how to use Python to read a file and manipulate local files safely through the Filesystem API. This server exposes 14 tools that AI clients can invoke during conversations and coding sessions.
How to install
You can install Filesystem in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
License
Filesystem is released under the NOASSERTION license.
Tools (14)
Read the complete contents of a file as text. DEPRECATED: Use read_text_file instead.
Read the complete contents of a file from the file system as text. Handles various text encodings and provides detailed error messages if the file cannot be read. Use this tool when you need to examine the contents of a single file. Use the 'head' parameter to read only the first N lines of a file, or the 'tail' parameter to read only the last N lines of a file. Operates on the file as text regardless of extension. Only works within allowed directories.
Read an image or audio file. Returns the base64 encoded data and MIME type. Only works within allowed directories.
Read the contents of multiple files simultaneously. This is more efficient than reading files one by one when you need to analyze or compare multiple files. Each file's content is returned with its path as a reference. Failed reads for individual files won't stop the entire operation. Only works within allowed directories.
Create a new file or completely overwrite an existing file with new content. Use with caution as it will overwrite existing files without warning. Handles text content with proper encoding. Only works within allowed directories.
Model Context Protocol servers
This repository is a collection of reference implementations for the Model Context Protocol (MCP), as well as references to community-built servers and additional resources.
[!IMPORTANT] If you are looking for a list of MCP servers, you can browse published servers on the MCP Registry. The repository served by this README is dedicated to housing just the small number of reference servers maintained by the MCP steering group.
[!WARNING] The servers in this repository are intended as reference implementations to demonstrate MCP features and SDK usage. They are meant to serve as educational examples for developers building their own MCP servers, not as production-ready solutions. Developers should evaluate their own security requirements and implement appropriate safeguards based on their specific threat model and use case.
The servers in this repository showcase the versatility and extensibility of MCP, demonstrating how it can be used to give Large Language Models (LLMs) secure, controlled access to tools and data sources. Typically, each MCP server is implemented with an MCP SDK:
- C# MCP SDK
- Go MCP SDK
- Java MCP SDK
- Kotlin MCP SDK
- PHP MCP SDK
- Python MCP SDK
- Ruby MCP SDK
- Rust MCP SDK
- Swift MCP SDK
- TypeScript MCP SDK
🌟 Reference Servers
These servers aim to demonstrate MCP features and the official SDKs.
- Everything - Reference / test server with prompts, resources, and tools.
- Fetch - Web content fetching and conversion for efficient LLM usage.
- Filesystem - Secure file operations with configurable access controls.
- Git - Tools to read, search, and manipulate Git repositories.
- Memory - Knowledge graph-based persistent memory system.
- Sequential Thinking - Dynamic and reflective problem-solving through thought sequences.
- Time - Time and timezone conversion capabilities.
Archived
The following reference servers are now archived and can be found at servers-archived.
- AWS KB Retrieval - Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
- Brave Search - Web and local search using Brave's Search API. Has been replaced by the official server.
- EverArt - AI image generation using various models.
- GitHub - Repository management, file operations, and GitHub API integration.
- GitLab - GitLab API, enabling project management.
- Google Drive - File access and search capabilities for Google Drive.
- Google Maps - Location services, directions, and place details.
- PostgreSQL - Read-only database access with schema inspection.
- Puppeteer - Browser automation and web scraping.
- Redis - Interact with Redis key-value stores.
- Sentry - Retrieving and analyzing issues from Sentry.io.
- Slack - Channel management and messaging capabilities. Now maintained by Zencoder
- SQLite - Database interaction and business intelligence capabilities.
🤝 Third-Party Servers
[!NOTE] The server lists in this README are no longer maintained and will eventually be removed.
🎖️ Official Integrations
Official integrations are maintained by companies building production ready MCP servers for their platforms.
21st.dev Magic - Create crafted UI components inspired by the best 21st.dev design engineers.
2slides - An MCP server that provides tools to convert content into slides/PPT/presentation or generate slides/PPT/presentation with user intention.
ActionKit by Paragon - Connect to 130+ SaaS integrations (e.g. Slack, Salesforce, Gmail) with Paragon’s ActionKit API.
Adfin - The only platform you need to get paid - all payments in one place, invoicing and accounting reconciliations with Adfin.
AgentOps - Provide observability and tracing for debugging AI agents with AgentOps API.
AgentQL - Enable AI agents to get structured data from unstructured web with AgentQL.AgentRPC - Connect to any function, any language, across network boundaries using AgentRPC.
- Agentset - RAG for your knowledge base connected to Agentset.
Airwallex Developer - Empowers AI coding agents with the tools they need to assist developers integrating with Airwallex APIs
Aiven - Navigate your Aiven projects and interact with the PostgreSQL®, Apache Kafka®, ClickHouse® and OpenSearch® services
Alation - Unlock the power of the enterprise Data Catalog by harnessing tools provided by the Alation MCP server.
Alby Bitcoin Payments - Connect any bitcoin lightning wallet to your agent to send and receive instant payments globally with your agent.- Algolia - Use AI agents to provision, configure, and query your Algolia search indices.
Alibaba Cloud AnalyticDB for MySQL - Connect to an AnalyticDB for MySQL cluster for getting database or table metadata, querying and analyzing data. It will be supported to add the OpenAPI for cluster operation in the future.
Alibaba Cloud AnalyticDB for PostgreSQL - An MCP server to connect to AnalyticDB for PostgreSQL instances, query and analyze data.
**[Alibaba Cloud DataWorks](https://github.com/aliyun/alib
README truncated. View full README on GitHub.
Related Skills
Browse all skillsExecution-layer skill for filesystem operations
Tauri path handling, cross-platform file operations, and API usage. Use when working with file paths in Tauri frontend code, accessing filesystem APIs, or handling platform differences in desktop apps.
Use this when you are working on file operations like reading, writing, scanning, or deleting files. It summarizes the preferred file APIs and patterns used in this repo. It also notes when to use filesystem helpers for directories.
This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.
Analyze disk space usage and filesystem information including mounts, usage, and large files
A shell for the web. Navigate URLs like directories, query pages with Unix-like commands. Activate on `websh` command, shell-style web navigation, or when treating URLs as a filesystem.