scanned 1mo ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓
DuckDB & MotherDuck MCP Server
This Model Context Protocol server exposes DuckDB — the fast in-process analytical database — and the MotherDuck cloud warehouse to AI agents through a single SQL tool. It is ideal for ad-hoc data analysis where an agent needs to query Parquet, CSV, or JSON without spinning up heavy infrastructure.
Key features
One query tool that runs arbitrary DuckDB SQL against local files or MotherDuck cloud databases
Directly reads Parquet, CSV, and JSON with DuckDB's zero-copy, columnar engine
Supports in-memory mode for throwaway analysis or a persistent .duckdb file
Optional MotherDuck token to attach shared cloud warehouses and hybrid local/cloud queries
Lightweight Python implementation installable via uvx, easy to add to any MCP client
Because DuckDB speaks standard SQL and handles gigabyte-scale files on a laptop, this server turns an agent into a capable, low-friction data analyst.
Curated mirror of the open-source mcp-server-motherduck (MIT). Get it from the source.
! Security: Review · 8888/100 · grade Bscanned 1mo ago
✓ no compromise signals11 risk-surface · 5/20 OWASP controls flagged
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
What this capability can do · high confidence (static)
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
OWASP Top 10 for LLM Applications
⚠LLM03Supply Chainhigh
Vulnerable/compromised dependencies, models or archives in the artifact.