Looker
A lightweight CLI and MCP server for automating Looker workflows, CI pipelines, and AI-assisted LookML development. Built by z3z1ma, it provides comprehensive tools for LookML parsing, validation, dependency analysis, query testing with baseline comparisons, and workspace management with persistent session storage. The implementation features SQLite-backed API caching for performance, SQL formatting capabilities, and both command-line interfaces and MCP server functionality for AI integration, making it valuable for data teams managing Looker instances, automating LookML quality checks in CI/CD pipelines, and enabling AI assistants to interact with Looker projects for code analysis and optimization.
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 2026-09-01.
Scan details: Circle-IR · 2026-09-01 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/z3z1ma/lookerctl
- Author type
- human
- Last scanned
- 2026-09-01
- Updated
- 2026-09-01
Use via MCP
Resolve Looker 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.