Skip to main content

MindsDB's AI SQL Server enables developers to build AI tools that need access to real-time data to perform their tasks

Project description


MindsDB enables humans, AI, agents, and applications to get highly accurate answers across sprawled and large scale data sources.

image

MindsDB has an MCP server built in that enables your MCP applications to connect, unify and respond to questions over large-scale federated data—spanning databases, data warehouses, and SaaS applications.

Minds Demo

Play with Minds demo, and see the power of MindsDB at answering questions from structured to unstructured data, whether it's scattered across SaaS applications, databases, or... hibernating in data warehouses like that $100 bill in your tuxedo pocket from prom night, lost, waiting to be discovered.

Install MindsDB Server

MindsDB is an open-source server that can be deployed anywhere - from your laptop to the cloud, and everywhere in between. And yes, you can customize it to your heart's content.

  • Using Docker Desktop. This is the fastest and recommended way to get started and have it all running.
  • Using Docker. This is also simple, but gives you more flexibility on how to further customize your server.
  • Using PyPI. This option enables you to contribute to MindsDB.

Core Philosophy: Connect, Unify, Respond

MindsDB's architecture is built around three fundamental capabilities:

Connect Your Data

You can connect to hundreds of enterprise data sources (learn more). These integrations allow MindsDB to access data wherever it resides, forming the foundation for all other capabilities.

Unify Your Data

Once connected, these data sources can be queried using a full SQL dialect, as if they were all part of a single database. MindsDB’s federated query engine translates your SQL queries and executes them on the appropriate connected data sources.

When working with many data sources, it’s important to prepare and unify your data before generating responses from it. MindsDB SQL offers virtual tables (views, knowledge bases, ml-models) to allow working with heterogeneous data as if it were unified in a single organized system.

  • VIEWS – Simplify data access by creating unified views across different sources (no-ETL).
  • KNOWLEDGE BASES – Index and organize unstructured data for efficient retrieval.
  • ML MODELS – Apply AI/ML transformations to gain insights from your data.

Unification of data can be automated using JOBs

  • JOBS – Schedule synchronization and transformation tasks for real-time processing.

Respond From Your Data

Chat with Your Data

  • AGENTS – Configure built-in agents specialized in answering questions over your connected and unified data.
  • MCP – Connect to MindsDB through the MCP (Model Context Protocol) for seamless interaction.

🤝 Contribute

Interested in contributing to MindsDB? Follow our installation guide for development.

You can find our contribution guide here.

We welcome suggestions! Feel free to open new issues with your ideas, and we’ll guide you.

This project adheres to a Contributor Code of Conduct. By participating, you agree to follow its terms.

Also, check out our community rewards and programs.

🤍 Support

If you find a bug, please submit an issue on GitHub.

Here’s how you can get community support:

For commercial support, please contact the MindsDB team.

💚 Current Contributors

Generated with contributors-img.

🔔 Subscribe for Updates

Join our Slack community

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mindsdb-25.6.3.0.tar.gz (6.2 MB view details)

Uploaded Source

Built Distribution

mindsdb-25.6.3.0-py3-none-any.whl (6.8 MB view details)

Uploaded Python 3

File details

Details for the file mindsdb-25.6.3.0.tar.gz.

File metadata

  • Download URL: mindsdb-25.6.3.0.tar.gz
  • Upload date:
  • Size: 6.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.15

File hashes

Hashes for mindsdb-25.6.3.0.tar.gz
Algorithm Hash digest
SHA256 d4638b6b4e1dfd7f638c87c190b7275f8af5a150ad3b14eaa53bc4478533816e
MD5 4209ac743703e1ab4dd4a5242eb73562
BLAKE2b-256 8a714869543940ec4d1018f03fdd0e309d9d64ab6a66cbe63a404362fbe89af1

See more details on using hashes here.

File details

Details for the file mindsdb-25.6.3.0-py3-none-any.whl.

File metadata

  • Download URL: mindsdb-25.6.3.0-py3-none-any.whl
  • Upload date:
  • Size: 6.8 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.15

File hashes

Hashes for mindsdb-25.6.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3a03300c15c64918a88ee10c646aa0505018c2173594d83ea9e76dddbd947ed7
MD5 4b88412e40679617ec89ddbb8eac585a
BLAKE2b-256 69f99147b4cc04347b13f35e3bb790ea70b7e5690318a0c7580b9c186472f370

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page