# GeiserX/duplicacy-mcp [Health: Active]

**Category:** 📊 Monitoring  
**Repository:** https://github.com/GeiserX/duplicacy-mcp  
**GitHub Stars:** 2  
**npm Downloads (last month):** 235  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/geiserx-duplicacy-mcp

## Description
Go-based MCP server for Duplicacy backup monitoring. Query backup job status and Prometheus metrics from a Duplicacy exporter. Docker image available.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "duplicacy-mcp": {
    "command": "npx",
    "args": ["-y","duplicacy-mcp"],
    "env": {
      "DUPLICACY_EXPORTER_URL": ""
    }
  }
}
```

**Requires environment variables:** `DUPLICACY_EXPORTER_URL` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What GeiserX/duplicacy-mcp MCP server does

GeiserX/duplicacy-mcp bridges a Duplicacy Prometheus exporter and MCP-compatible clients. It reads the exporter’s backup metrics and makes them available for agent-driven monitoring of backup state, progress, and health.

The server is intended for read-oriented inspection rather than backup administration. It exposes three MCP resources—`duplicacy://status`, `duplicacy://progress`, and `duplicacy://health`—for browsing current monitoring information. Four tools provide more targeted queries: `get_backup_status`, `get_backup_history`, `list_snapshots`, and `get_prune_status`.

## How it works

The MCP process retrieves metrics from `duplicacy-exporter`, whose endpoint is supplied through configuration. Clients can communicate with the server over a single JSON-RPC endpoint at `/mcp`, or start it as a local stdio process through the npm package.

The HTTP mode listens on `127.0.0.1:8080` by default. This keeps the default listener local; deployments that make the endpoint reachable beyond the host should place an authenticated reverse proxy in front of it.

## Setup and configuration

The server can be run as a Docker container, through the npm package, or from one of the published Go binaries. A Docker deployment maps the local port to port 8080 and sets `DUPLICACY_EXPORTER_URL` to the exporter address, such as `http://duplicacy-exporter:9750`.

For stdio clients, configure the npm package as the command and pass `-y duplicacy-mcp` as its arguments. The exporter URL is supplied in the client’s environment configuration. A local build and Docker Compose setup are also available as deployment options.

The HTTP endpoint is available at `http://127.0.0.1:8080/mcp` with the default listener settings. The project also distributes an npm wrapper, Docker image, and Go binaries for multiple platforms.

## Tools and capabilities

- `get_backup_status` queries backup job status.
- `get_backup_history` retrieves historical backup information.
- `list_snapshots` lists available Duplicacy snapshots.
- `get_prune_status` reports pruning status.
- `duplicacy://status` provides a read-only status resource.
- `duplicacy://progress` provides a read-only progress resource.
- `duplicacy://health` provides a read-only health resource.

Together, these interfaces cover current backup state, progress, health, historical activity, snapshots, and pruning information derived from the exporter.

## Limitations and notes

The server depends on a reachable Duplicacy exporter and uses its metrics as the source of monitoring data. It is designed to expose monitoring information through MCP; the listed resources are read-only. The default HTTP listener is local to the machine, and an authentication-capable reverse proxy is recommended before exposing the endpoint more broadly.

_Full upstream README: https://allmcps.com/mcp/geiserx-duplicacy-mcp/readme_