Which directories does the server have access to?
Only the directories specified via command-line arguments at startup. The server will refuse operations outside these paths.
Filesystem MCP Server SSE
@ysthink
基本情報
Filesystem MCP Server SSE について
The SSE version of the MCP service is modified from the Filesystem MCP server
Filesystem MCP Server SSE の設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"Filesystem-MCP-Server-SSE": {
"command": "docker",
"args": [
"build",
"-t",
"mcp/filesystem",
"-f",
"Dockerfile",
"."
]
}
}
}Filesystem MCP Server SSE のツール
10Read complete contents of a file
Read multiple files simultaneously
Create new file or overwrite existing (exercise caution with this)
Make selective edits using advanced pattern matching and formatting
Create new directory or ensure it exists
List directory contents with [FILE] or [DIR] prefixes
Move or rename files and directories
Recursively search for files/directories
Get detailed file/directory metadata
List all directories the server is allowed to access
概要
What is Filesystem MCP Server SSE?
Filesystem MCP Server SSE is a Node.js server that implements the Model Context Protocol (MCP) for filesystem operations, allowing AI assistants to read, write, and manage files and directories. It is intended for users who need sandboxed filesystem access via MCP.
How to use Filesystem MCP Server SSE?
Install dependencies with npm install, build, and run the server with the allowed directories as arguments (e.g., node .\dist\index.js C:\Users\User\Desktop\project). Alternatively, use Docker by building the image and mounting directories to /projects. Configure your MCP client (e.g., Cherry Stdio Desktop) to point baseUrl to the server's SSE endpoint.
Key features of Filesystem MCP Server SSE
- Read, write, and edit files with advanced pattern matching
- Create, list, and delete directories
- Move or rename files and directories
- Recursive file search with exclude patterns
- Get detailed file metadata (size, timestamps, permissions)
Use cases of Filesystem MCP Server SSE
- An AI coding assistant reads and modifies source files in a project directory
- Automated file organization: move, rename, or delete files based on criteria
- Preview file edits with dry-run mode before applying changes
- List allowed directories to verify sandbox boundaries
よくある質問
How can I preview edits before applying?
Use the `edit_file` tool with the `dryRun` parameter set to `true`. The server returns a diff and match information without modifying the file.
What happens if I try to move a file to a destination that already exists?
The `move_file` operation fails if the destination already exists, to prevent accidental overwrites.
How do I run the server using Docker?
Build with `docker build -t mcp/filesystem .` and run with `docker run -i --mount type=bind,src=...` mounting allowed directories under `/projects`. See the README for full command.
Can I read multiple files at once?
Yes, use the `read_multiple_files` tool with an array of paths. Failed reads do not stop the entire operation.
「ファイルとストレージ」の他のコンテンツ
Claude Document MCP Server
alejandroBallesterosCA lightweight MCP server for processing, editing, and interacting with PDF, Word, Excel, and CSV documents.
51
DeviceLink
Jayanka SampathDeviceLink lets you share folders from your computer with AI assistants, securely and in real-time. Nothing is uploaded. Your files stay on your machine, and are only accessible while the device sharing them is connected
Google Drive
modelcontextprotocolModel Context Protocol Servers
88.1K
drop.media
drop.mediaUpload once. Find, use and share across your AI workflows. drop.media is one media library for you and every AI agent you use: files added from Claude, ChatGPT, Cursor, the terminal or the web can be found, reused and sh
S3 MCP Server
samuraikunMCP server to integrate AWS S3 and LLM
26
コメント