What dependencies are required to run the server?
Docker is the primary method; alternatively, Python 3 with the packages in `requirements.txt`. The HTTP/SSE deployment also installs `mcp-proxy`.
@atom2ueki
Basic information
πΎ Model Context Protocol (MCP) server for Synology NAS - Enables AI assistants (Claude, Cursor, Continue) to manage files, downloads, and system operations through secure API integration. Features Docker deployment, auto-authentication, and comprehensive file system tools.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-server-synology": {
"command": "python",
"args": [
"main.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A Model Context Protocol (MCP) server for Synology NAS devices. It enables AI assistants like Claude and Cursor to manage files, downloads, and system health through secure authentication and session management. The unified server supports both Claude/Cursor (stdio) and Xiaozhi (WebSocket) simultaneously.
Clone the repository, copy env.example to .env, and configure the Synology NAS URL, username, and password. Run with docker-compose up -d (or python main.py for local execution). Then add the server to your MCP client (Claude Desktop, Cursor, Continue, or Codeium) using the provided JSON configuration. For remote access, deploy with the HTTP/SSE image and front with a TLS-terminating reverse proxy.
Docker is the primary method; alternatively, Python 3 with the packages in `requirements.txt`. The HTTP/SSE deployment also installs `mcp-proxy`.
Use the provided `docker-compose.http.yml` file to expose the MCP server over HTTP/SSE on port 8765, then front it with a reverse proxy (DSM Login Portal, Nginx, etc.) for TLS termination and optional authentication.
Yes. When `ENABLE_XIAOZHI=true` is set in `.env`, the server acts as a bridge serving both stdio (for Claude/Cursor) and WebSocket (for Xiaozhi) at the same time.
The server authenticates with the Synology NAS using the credentials stored in the `.env` file (`SYNOLOGY_USERNAME`, `SYNOLOGY_PASSWORD`). The HTTP/SSE endpoint itself has no built-in authentication; it should be secured at the reverse proxy level.
Yes. Add the same Docker (or Python) configuration as for Claude/Cursor to your `./continue/config.json` `mcpServers` block.
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
TestMu AI MCP Server lets developers run, debug, and triage tests through natural language directly from their IDE (Cursor, Claude, GitHub Copilot, and other MCP clients). It exposes five tools β HyperExecute (test orche
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Eased is a library of motion-first React components for shadcn, installed with the shadcn CLI.
Comments