Gigapipe
This MCP server provides unified access to Gigapipe's observability platform, enabling AI assistants to query Prometheus metrics with PromQL, search Loki logs with LogQL, and retrieve Tempo traces by ID through a single interface. Built in Go using the mcp-go library, it connects to Gigapipe instances via HTTP/HTTPS with optional basic authentication, offering tools for metric queries with time ranges and step intervals, log searches with configurable limits, trace retrieval in JSON format, and label/tag discovery across all three data sources. The implementation includes cross-platform binary releases for Linux, macOS, and Windows, making it valuable for DevOps teams monitoring distributed systems, SRE workflows requiring correlation between metrics, logs, and traces, and automated troubleshooting scenarios that need to query multiple observability data types through a unified API.
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/gigapipehq/gigapipe-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Gigapipe 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.