Observability Agent MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| observability.capabilitiesA | Describe enabled read-only observability tools and bounded limits. |
| observability.health_snapshotC | Return bounded health evidence for logical services. |
| observability.active_alertsC | Return normalized active alert metadata. |
| observability.query_metricsC | Run a bounded named metrics query. |
| observability.render_panelA | Render one allowlisted logical panel as bounded PNG evidence. |
| observability.render_dashboardB | Render one allowlisted agent-safe dashboard as bounded PNG evidence. |
| observability.incident_contextC | Build bounded health, alert, metric, and optional visual context. |
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 7 tools
Each tool targets a distinct observability artifact—dashboards, panels, health, alerts, metrics, capabilities, and incident context. The only mild ambiguity is between render_dashboard and render_panel (both emit PNGs) and between incident_context and the individual query tools, but descriptions clarify the aggregation vs. single-purpose distinction.
All tools share the consistent 'observability.' prefix and snake_case, but only render_dashboard, query_metrics, and render_panel follow a verb_noun pattern; capabilities, health_snapshot, active_alerts, and incident_context are noun phrases. The mixed style is readable but not fully predictable.
Seven tools is a well-scoped size for a read-only observability server, fitting comfortably in the ideal 3–15 range. Each tool has a clear purpose with no redundancy.
The surface covers the core observability workflows: discovery, health, alerts, metrics, visual evidence at both dashboard and panel levels, and an incident context aggregator. Minor gaps exist—no log or trace search, and no explicit listing of allowlisted dashboards/metrics—but the capabilities tool mitigates discovery concerns.