beszel-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BESZEL_URL | Yes | Beszel/PocketBase URL (e.g. http://localhost:8090) | |
| BESZEL_EMAIL | No | Admin email for authentication | |
| BESZEL_PASSWORD | No | Admin password 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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_systemsB | List all monitored systems in Beszel with their status and metadata. |
| list_containersA | List all monitored containers running on Beszel-managed systems. |
| list_alertsA | List all configured alerts in Beszel including thresholds and notification settings. |
| list_alert_historyA | List historical records of triggered alerts in Beszel. |
| query_system_statsA | Query time-series statistics for a specific system (CPU, memory, disk, network). |
| query_container_statsA | Query time-series statistics for a specific container (CPU, memory, network). |
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 6 tools
Each tool targets a distinct resource or action: alerts vs alert history, containers vs systems, and stats queries are clearly separated by entity type.
All tools follow a consistent verb_noun pattern: 'list_' for listing entities and 'query_' for time-series statistics, with no deviations.
6 tools is well-scoped for a monitoring server, covering essential listing and querying operations without being too few or excessive.
The set covers core monitoring tasks (listing resources, querying stats, viewing alerts) but lacks alert management (create/update/delete) or container log access, though these may be out of scope.