QueryWeaver
QueryWeaver is a text-to-SQL system that combines FastAPI with graph-powered schema understanding using FalkorDB to enable natural language database querying. The implementation features PostgreSQL and MySQL schema loaders that extract database structures into graph representations with vector embeddings, multi-agent query processing pipeline with analysis, relevancy checking, and response formatting agents, and OAuth-based authentication with API token management. Built with a modular architecture supporting both web interface and MCP protocol integration, it enables use cases like business intelligence queries, database exploration, and automated report generation by translating conversational questions into accurate SQL queries while maintaining context across query sessions.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · 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/falkordb/queryweaver
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve QueryWeaver 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.