What directories can the server access?
The server only accesses directories that are explicitly passed as arguments at startup. The `list_allowed_directories` tool returns this list.
@mark3labs
基本信息
Go server implementing Model Context Protocol (MCP) for filesystem operations.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-filesystem-server": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/mark3labs/mcp-filesystem-server:latest",
"/path/to/allowed/directory"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
MCP Filesystem Server provides secure access to the local filesystem through the Model Context Protocol (MCP). It is intended for applications that support MCP and need controlled file read, write, search, and directory operations.
Install via go install github.com/mark3labs/mcp-filesystem-server@latest. Start the server by specifying one or more allowed directories as arguments, for example mcp-filesystem-server /path/to/allowed/directory. It can also be used as a Go library or run in Docker. Integrate with MCP-compatible apps by adding the server to the mcpServers configuration.
The server only accesses directories that are explicitly passed as arguments at startup. The `list_allowed_directories` tool returns this list.
It performs path validation to prevent directory traversal attacks and symlink resolution with security checks, ensuring operations stay within allowed directories.
Yes. A Docker image is available at `ghcr.io/mark3labs/mcp-filesystem-server:latest`. You can mount host volumes to allow the container to modify files on the host.
It supports text, binary, and image files. MIME type detection is included.
Yes, the server enforces size limits for inline content and base64 encoding, though the exact limits are not specified in the README.
Blazing-fast, asynchronous MCP server for seamless filesystem operations.
Manage your Hevy workouts, routines, folders, and exercise templates. Create and update sessions faster, organize plans, and search exercises to build workouts quickly. Stay synced with changes so your training log is always up to date.
filesystem MCP server for accessing WSL distributions from Windows
MCP Server for reading many files at the same time
MCP server that exposes a V8 JavaScript runtime as a tool for AI agents like Claude and Cursor. Supports persistent heap snapshots via S3 or local filesystem, and is ready for integration with modern AI development environments.
评论