woodpecker-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WP_PROM_URL | No | Prometheus URL (or any PromQL-compatible backend) | http://localhost:9091 |
| WP_TOPOLOGY | No | Topology connector: docker, k8s, or traces (Jaeger) | docker |
| WP_AUTO_REFRESH | No | 0 queries a static snapshot without rebuilding | 1 |
| WP_GRAPH_BACKEND | No | Graph backend: falkordb (server) or kuzu (embedded) | falkordb |
| WP_METRICS_BACKEND | No | Metrics connector: prometheus or datadog | prometheus |
| WP_MONITORED_SERVICES | No | Services expected to be scraped (blind-spot check) | web,orders,db |
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 |
|---|---|
| woodpecker_get_topologyA | Return the materialized service dependency graph: every service, its current status, and the services it depends on. Call first to establish the causal structure before diagnosing. status in {healthy, erroring, unhealthy, restarting, hung, down}; monitoring='MISSING' flags a possible blind spot. |
| woodpecker_diagnose_root_causeA | Localize the ROOT CAUSE deterministically: the DEEPEST failing service, the unhealthy one whose own dependencies are all healthy. Everything unhealthy above it is cascading fallout. Returns root cause(s), the causal chain per cascading symptom, blast radius, blind spots, and a page/no-page verdict, distinguishing a real outage from an observability blind spot (metrics missing but the service responds). Exact and repeatable, unlike per-investigation inference. |
| woodpecker_get_blast_radiusA | Transitive dependency closure of a service over DEPENDS_ON edges. direction='upstream': services that transitively depend on this one (its blast radius if it fails). direction='downstream': everything it relies on (trace toward a deeper root cause). |
| woodpecker_get_service_healthA | Detailed health snapshot for one service: status, container state/health, restarts, 5xx error rate, db pg_up, scrape health, and blind-spot flag. |
| woodpecker_detect_blind_spotsA | List observability blind spots: services that are healthy but have no live Prometheus scrape target (lost visibility, NOT an outage - do not page). |
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 5 tools
Each tool serves a distinct role: detecting blind spots, diagnosing root causes, computing blast radius, providing service health, and retrieving topology. Minimal overlap, clear boundaries.
All tools follow a consistent 'woodpecker_verb_noun' pattern using snake_case, e.g., woodpecker_detect_blind_spots, woodpecker_get_topology. No deviations.
With 5 tools covering topology, health, blind spots, root cause, and blast radius, the set is well-scoped for diagnostic purposes without being excessive or thin.
The set provides a complete workflow for service dependency analysis: establish topology, check health, detect blind spots, find root cause, and compute blast radius. No obvious gaps for the intended domain.