prometheus-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 |
|---|---|
| prometheus_list_metricsA | List all available Prometheus metrics |
| prometheus_metric_metadataB | Get metadata for a specific Prometheus metric |
| prometheus_list_labelsA | List all available Prometheus labels |
| prometheus_label_valuesA | Get all values for a specific Prometheus label |
| prometheus_list_targetsB | List all Prometheus targets |
| prometheus_scrape_pool_targetsA | Get targets for a specific scrape pool |
| prometheus_runtime_infoB | Get Prometheus runtime information |
| prometheus_build_infoA | Get Prometheus build information |
| prometheus_queryC | Execute a Prometheus query |
| prometheus_query_rangeB | Execute a Prometheus range query |
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 10 tools
Most tools target distinct Prometheus resources, and the descriptions make the boundaries clear. The main ambiguities are list_targets vs scrape_pool_targets and list_labels vs label_values, which are related but scope-differentiated.
All tool names share the prometheus_ prefix and snake_case, but the pattern is mixed: some use list_* verbs, others use bare nouns like runtime_info or query_range. This is readable but not a consistent verb_noun convention.
Ten tools is well-scoped for a Prometheus MCP server, covering querying, metadata, targets, and informational endpoints without unnecessary bloat.
The surface covers core query, range query, metric metadata, label values, and target discovery. Missing alerting/rules or series endpoints, but the main monitoring workflows are well supported.