Outils

In-process analytical SQL database. Its CLI queries CSV, Parquet and JSON files directly with SQL, no import or server needed, so agents can sample and aggregate large files. Officially maintained.

Google's open-source database MCP server with ready-made query and SQL tools for dozens of sources, including PostgreSQL, MySQL, BigQuery, Spanner and MongoDB. Define controlled custom queries in tools.yaml.

Anthropic's official data skill that guides agents to write, translate and optimize SQL across Snowflake, BigQuery, Databricks, PostgreSQL and other warehouse dialects, including CTEs, window functions and analytical aggregations.

Manages BigQuery datasets, tables and jobs with the bq and gcloud CLIs, runs SQL queries and loads data, with references for client libraries, MCP and Terraform. Google's official skill; requires a Google Cloud project.

PostgreSQL command-line client with smart autocompletion and syntax highlighting. Compatible with psql environment variables, and -c runs a statement and exits, so agents can query databases non-interactively.

MySQL terminal client with smart autocompletion and syntax highlighting, also compatible with MariaDB and TiDB. Supports --execute and batch mode with CSV or table output, so agents can run SQL directly.

Publishes SQLite databases as browsable, queryable web pages and JSON APIs, with SQL queries, metadata and plugins, and deploys to Cloud Run and other platforms with datasette publish. Great for data exploration and data journalism. Needs Python 3.10+.

Universal psql-style SQL command line: one tool to connect to PostgreSQL, MySQL, SQLite, SQL Server, Oracle and dozens of other SQL and NoSQL databases, with support for copying data between databases.

One server connecting PostgreSQL, MySQL, MariaDB, SQL Server, Oracle and SQLite, exposing just two tools by default to save context, with read-only mode and SSH tunneling. From Bytebase.

Framework for writing data transformation models in SQL or Python, with a Terraform-like plan/apply flow, virtual data environments, unit tests and table diffs, and transpilation across 10+ SQL dialects. A Linux Foundation project and an alternative to dbt.

A CLI and Python library by Simon Willison: imports JSON and CSV straight into SQLite with automatic table creation, runs in-memory SQL queries over files, and supports full-text search and table transformations.

Gives agents controlled access to MySQL: list databases and tables, inspect schemas and sample data, and run SQL, with multi-database mode, SSL and SSH tunnels. Configure your own database user, ideally with least privilege.

Runs SQL queries against ClickHouse and browses databases and table schemas, read-only by default; can also enable embedded chDB to query data directly in files and URLs. Maintained by ClickHouse.

Official DuckDB skills: query local or S3 CSV, Parquet, Excel and JSON files with SQL or plain language, attach databases, convert formats, analyze spatial data and look up documentation. Needs the DuckDB CLI; tested only on macOS and Linux.

Official ClickHouse skills: best practices for schema design, primary keys, JOINs and inserts ranked by impact, advice on real-time architecture decisions, in-process SQL and pandas-compatible analysis with chDB, and local and cloud deployment workflows.

Official Databricks skills guiding agents to build Lakeflow pipelines and jobs, Apps, Lakebase, Vector Search, Model Serving and AI/BI dashboards on the lakehouse. Needs the Databricks CLI.

Apache Doris's official MCP: gives agents read-only access to explore table metadata, run and explain SQL, diagnose slow queries, and check cluster status, load jobs and data governance info. Needs Python 3.12+ and Doris 2.0 or later.

Snowflake's official plugin: detects Snowflake-related requests and hands them to the Cortex Code CLI, whose 55+ built-in skills handle SQL, dynamic tables, data governance and more. Needs the cortex CLI installed and a Snowflake connection configured.