mcp-centreon
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CENTREON_HOST | Yes | Centreon server hostname or IP (without https://) | |
| CENTREON_PASSWORD | Yes | Centreon login password | |
| CENTREON_USERNAME | No | Centreon login username | admin |
| CENTREON_ALLOW_SELF_SIGNED | No | Accept self-signed TLS certificates (true/false) | true |
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_hostsA | List monitored hosts in Centreon. Filter by name, state, or page through results. |
| get_hostA | Get full details for a specific host by its ID. |
| list_host_groupsA | List host groups configured in Centreon with member counts. |
| acknowledge_hostB | Acknowledge a host problem in Centreon to suppress notifications. |
| add_downtime_hostB | Schedule a downtime for a host in Centreon to suppress notifications during maintenance. |
| list_servicesA | List monitored services in Centreon. Filter by host, state, or service name. |
| get_serviceA | Get full details for a specific service by host ID and service ID. |
| list_service_groupsC | List service groups configured in Centreon. |
| acknowledge_serviceB | Acknowledge a service problem in Centreon to suppress notifications. |
| add_downtime_serviceB | Schedule a downtime for a service in Centreon to suppress notifications during maintenance. |
| list_eventsC | List recent monitoring events and alerts in Centreon. Filter by host, state, or check type. |
| list_acknowledgementsA | List active acknowledgements in Centreon — who acknowledged what and when. |
| list_downtimesA | List active and scheduled downtimes in Centreon. |
| get_service_metricsA | Get the list of performance metrics available for a specific service. Use this to discover metric names before fetching time-series data. |
| get_metrics_dataA | Get time-series performance data for a specific metric of a service. Use get_service_metrics first to discover available metric names. |
| get_platform_statusA | Get platform-level statistics for the Centreon monitoring system: total host and service counts broken down by state. |
| get_poller_listA | List Centreon pollers and remote servers with their connectivity status from the platform topology. |
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 17 tools
Each tool targets a distinct resource and action (list vs get, host vs service, acknowledge vs downtime, metrics discovery vs data retrieval). No two tools appear to do the same thing, and action verbs clearly differentiate between read and write operations.
All tool names follow a consistent verb_noun pattern (get_, list_, acknowledge_, add_downtime_), using snake_case throughout. The pattern is predictable and makes it easy to guess the purpose of a tool from its name.
At 17 tools, the server is slightly above the ideal 3-15 range but each tool serves a distinct purpose within the monitoring domain. The count feels justified, covering hosts, services, groups, events, acknowledgements, downtimes, metrics, and pollers, though it is a bit heavy.
The tool surface covers the core monitoring lifecycle: viewing hosts/services, acknowledging problems, scheduling downtimes, and fetching performance metrics. Missing operations like canceling a downtime or listing acknowledgements in detail are minor gaps that agents could work around, but the set is largely complete for common monitoring tasks.