mcp-prtg
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PRTG_URL | Yes | URL of your PRTG server (e.g., https://prtg.example.com) | |
| PRTG_PASSHASH | Yes | Passhash for the PRTG user | |
| PRTG_USERNAME | Yes | PRTG username for authentication |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_sensorsA | List PRTG sensors with optional filters. Args: id: Parent object ID (device or group) to filter sensors under. status: Filter by status: up, down, warning, paused, unknown, unusual, down_acknowledged, down_partial. tags: Filter by tag, e.g. @tag(mytag). text_filter: Filter sensors whose name contains this text. count: Max results (default 500). |
| get_sensor_detailsB | Get full details for a specific sensor. Args: id: The sensor object ID. |
| get_channelsB | List all channels for a specific sensor. Args: id: The sensor object ID. |
| get_devicesA | List PRTG devices with optional filters. Args: id: Parent group ID to list devices under. text_filter: Filter devices whose name contains this text. count: Max results (default 500). |
| get_groupsA | List PRTG groups (used to organize devices). Args: id: Parent group ID to list sub-groups under. count: Max results (default 500). |
| get_sensor_historyA | Get historic monitoring data for a sensor. Args: id: The sensor object ID. sdate: Start date/time as YYYY-MM-DD-HH-MM-SS. edate: End date/time as YYYY-MM-DD-HH-MM-SS. avg: Averaging interval in seconds. 0=raw, 300=5min, 3600=1h, 86400=1day. count: Max data points (default 500). |
| get_server_statusA | Get overall PRTG server health and sensor counts. |
| get_messagesA | Get PRTG system log messages. Args: id: Object ID to filter messages for. count: Max messages (default 100). date_range: Relative date filter: today, yesterday, 7days, 30days, 6months, 12months. |
| searchA | Search PRTG objects by name. Args: query: Text to search for in object names. type: Object type: sensors, devices, or groups. count: Max results (default 50). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool targets a distinct aspect of PRTG monitoring, such as listing groups, devices, sensors, channels, history, and server status. There is no overlap or ambiguity between them.
Most tools follow a consistent 'get_' prefix pattern (e.g., get_sensors, get_groups). The only exception is 'search', which breaks the pattern but is still a clear verb for its purpose.
With 9 tools, the server is well-scoped for a PRTG monitoring client. Each tool provides a necessary function without redundancy, covering listing, details, history, and status.
The tool surface covers core read operations for PRTG monitoring (groups, devices, sensors, channels, history, messages, status, search). Minor gaps exist, such as missing support for thresholds or notifications, but overall it's solid.