Awesome Openclaw Skills
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞.
The official Model Context Protocol server for secure filesystem access — read, write, search, and navigate files from AI clients within configured directory boundaries.
Runs as an MCP server exposing filesystem tools (read_file, write_file, list_directory, search_files) over the Model Context Protocol via stdio. AI clients like Claude Desktop connect and can safely operate on local files within the directories you allowlist.
Autonomous filesystem traversal, batch file restructuring, and format transformations
Event-driven command execution and script orchestration within scoped project boundaries
Integration into autonomous agent loops for continuous integration and task verification
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem"
]
}
}
}
Paste into your client configuration file (e.g. ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%/Claude/claude_desktop_config.json on Windows).
Install Node.js 18 or newer
Add the server in your client config (e.g. Claude Desktop claude_desktop_config.json) with npx -y @modelcontextprotocol/server-filesystem /path/to/allowed/dir
Restart the AI client to load the MCP server
Ask the client to read, create, or search files inside the allowed directory
Keeps heavy parsing and raw file structures external to the LLM. Only sanitized excerpts and structured returns are injected into agent memory turns.
Enforce explicit directory allowlists and permission scopes in client configuration to ensure autonomous tool calls never breach system boundaries.
Executes in an isolated local child process communicating strictly over JSON-RPC via stdio with explicit process timeouts.
Filesystem MCP Server is an open-source automation capability designed for AI clients and autonomous agents. The official Model Context Protocol server for secure filesystem access — read, write, search, and navigate files from AI clients within configured directory boundaries.
Follow the step-by-step installation: 1) Verify your runtime (Node.js 18+), 2) Add the configuration snippet into your AI client settings (e.g. claude_desktop_config.json), 3) Restart the client to initialize tool execution.
Filesystem MCP Server is compatible with all AI tools supporting tool-calling and the Model Context Protocol (MCP), including Claude Desktop, Cursor, Claude Code CLI, Windsurf, OpenCode, and custom agent runtimes.
Filesystem MCP Server executes locally with strict directory allowlists and permission scopes. Heavy parsing and raw file structures stay external to the LLM context window to prevent memory saturation and unauthorized access.
Yes, Filesystem MCP Server is published under the MIT open-source license. You can inspect the source code and contribute on GitHub at https://github.com/modelcontextprotocol/servers.
Explore open-source implementation code, license, and community releases.
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞.
An open-source reference implementation of Langgraph for AI and LLM workflows.
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra.
This example demonstrates how to connect an ADK agent to a filesystem MCP server using the MCPToolset. The agent can perform file operations like reading, writing, and listing files through the Model Context Protocol.
MCP AI AgentsAgentScout is an always-on Hacker News briefing agent built with Google ADK. It scans Hacker News for high-signal stories about AI agents, MCP, coding agents, workflow automation, and LLM apps, then turns a featured links into a concise...
Game Playing AgentsThis Project demonstrates R1's code capabilities with a PyGame code generator and visualizer with browser use. The system uses DeepSeek for reasoning, OpenAI for code extraction, and browser automation agents to visualize the code on...