A
licenseA
qualityA
maintenanceAn MCP server for MotherDuck and local DuckDB.
10
5
536
MIT
Best DuckDB MCP Servers
DuckDB is an in-process SQL OLAP database management system designed for analytical queries with a simple, embeddable architecture that supports various programming languages and platforms.
Why this server?
Integrates with local DuckDB to provide SQL analytics capabilities and allow querying data from local databases
Why this server?
Provides DuckDB as the built-in local warehouse for Semantic Rails, supporting semantic queries, validation, and execution without additional connectors.
AlicenseBqualityBmaintenanceEnables agents to interact with a governed semantic layer for querying and authoring metrics, providing tools for discovery, planning, validation, and execution of analytics queries.302Apache 2.0Why this server?
Enables writing Parquet files to object storage that DuckDB can load or query, supporting analytics workflows.
Why this server?
Allows running data quality validation rules against a DuckDB database, including completeness, uniqueness, and statistical checks.
AlicenseBqualityDmaintenanceAgentic data quality MCP server — runs structured validation rules against warehouses (DuckDB, BigQuery, Athena, Databricks, Postgres), diagnoses failures with LLM root cause analysis, and proposes SQL remediations. Full audit trail of every AI decision.64Apache 2.0Why this server?
Runs read-only SQL against DuckDB, querying CSV, Parquet and JSON files or an existing .duckdb database, describing columns/types/row counts and samples, and writing query results out to .csv, .tsv, .parquet or .json/.ndjson files (never overwriting an existing file unless overwrite=True).
faraztools-mcpofficial
AlicenseAqualityCmaintenanceEnables AI clients to call small utility tools like echo and Markdown-to-PDF conversion, running locally over stdio.2MITWhy this server?
Allows querying financial evidence from money markets, bank risk, market liquidity, and China economy data through DuckDB using HTTP-backed views.
AlicenseAqualityAmaintenancePublic MCP research for AI finance and trading agents: funding, bank risk and liquidity evidence. Companion SDK: persistent Python MCP sessions and Python/JS source-status streams. Setup: https://beepboop2025.github.io/financial-evidence-skills/distribution/ai-trading-tools.html. No data API key. Keep source dates, rights and gaps. No live quotes or execution.23209 PyPI1MITWhy this server?
Provides spatial SQL execution using DuckDB's dialect, including ST_* functions and file reading via read_parquet/ST_Read, enabling SQL-based geoprocessing and materialization of results as GeoParquet with provenance.
MapSmithofficial
AlicenseAqualityAmaintenanceEnables AI agents to perform professional-grade geoprocessing tasks such as buffers, overlays, reprojections, and terrain analysis with deterministic tools and verifiable provenance.29146 PyPI2AGPL 3.0Why this server?
Uses DuckDB as an embedded analytical database engine.
Why this server?
Enables arbitrary SQL queries on property data through the queryProperties tool using embedded DuckDB.
AlicenseAqualityAmaintenanceConnects Claude-compatible clients to the Elephant data graph, enabling discovery of data groups, classes, and property schemas. Supports semantic code search for verified script examples via OpenAI or AWS Bedrock embeddings.108 npm2MIT
