Prometheus
This MCP server provides direct access to Prometheus monitoring systems, enabling instant and range queries, metric discovery, and metadata retrieval through a robust HTTP client with built-in retries, caching, and rate limiting. Built by Breno A. in Rust, it supports both CLI usage and MCP server modes, handles Basic Auth for secure Prometheus instances, and includes an optional internal metrics exporter for self-observability. The implementation offers comprehensive Prometheus API coverage including series selectors, label value enumeration, and metric metadata lookup, making it valuable for DevOps workflows, system monitoring analysis, and troubleshooting scenarios where users need to query and analyze metrics data through conversational interfaces rather than navigating Prometheus dashboards directly.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/brenoepics/prometheus-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Prometheus from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.