Wren Engine

What is Wren Engine about?

Wren Engine delivers a semantic layer for Model Context Protocol (MCP) clients and AI agents. It translates natural‑language intent into accurate, governed SQL queries across a wide range of data sources, ensuring that AI‑driven workflows retrieve the right data in the right context.

How to use Wren Engine?

1. Deploy the MCP server – follow the mcp-server/README.md to start the Python‑based MCP server.
2. Connect data sources – configure connections for BigQuery, Snowflake, PostgreSQL, MySQL, etc., via the provided API endpoints.
3. Define semantic models using the Modeling Definition Language (MDL) in the wren-core layer.
4. Integrate with an MCP client (e.g., Claude, Cursor) or an AI agent; the client sends intents to the MCP server, which resolves them to semantic‑aware SQL and returns results.
5. Consume the results in downstream BI dashboards, CRM updates, or automated workflows.

Key features of Wren Engine

• Embeddable: can be packaged into any MCP client or agentic workflow.
• Interoperable: supports major cloud and on‑prem databases (PostgreSQL, MySQL, Snowflake, Trino, etc.) and file storage (S3, GCS, Minio, local files).
• Semantic‑first: MDL‑driven data models give AI agents business‑level concepts like "active customer" or "net revenue".
• Governance‑ready: role‑based access control, permission enforcement, and trustworthy aggregations.
• Fast query engine: Rust‑based core powered by Apache DataFusion for high‑performance SQL execution.
• Developer‑friendly modules: FastAPI/Ibis web server, Python bindings, and MCP server packaged separately.

Use cases of Wren Engine

• AI‑augmented business intelligence – natural‑language queries in dashboards that respect data definitions and security.
• Automated CRM updates – agents retrieve and update customer records based on contextual intent.
• Compliance and audit workflows – ensured that every data access follows predefined governance policies.
• Data‑driven chatbots – conversational agents that can fetch accurate metrics and perform calculations on the fly.
• Integration with low‑code platforms – Zapier or similar tools can call the MCP server to trigger data‑centric actions.

FAQ from the Wren Engine

• Do I need to write SQL manually? No. Define semantic models with MDL and let the engine translate natural language into SQL.
• Which databases are supported? BigQuery, Snowflake, PostgreSQL, MySQL, MS SQL Server, Oracle, Trino, and file storage like S3, GCS, Minio, plus local files.
• Is the project production‑ready? It is currently in beta with bi‑weekly releases; many enterprises are already testing it in pilot projects.
• How is security handled? Access control is enforced at the semantic layer, respecting user roles and permissions defined in the model.
• Can I extend the engine? Yes. You can add custom functions in the Rust core or expose additional APIs via the FastAPI server.

Wren Engine is the Semantic Engine for MCP Clients and AI Agents. Wren AI GenBI AI Agent is based on Wren Engine.

🔌 Supported Data Sources

• BigQuery
• Google Cloud Storage
• Local Files
• MS SQL Server
• Minio
• MySQL Server
• Oracle Server
• PostgreSQL Server
• Amazon S3
• Snowflake
• Trino

😫 Challenge Today

At the enterprise level, the stakes - and the complexity - are much higher. Businesses run on structured data stored in cloud warehouses, relational databases, and secure filesystems. From BI dashboards to CRM updates and compliance workflows, AI must not only execute commands but also understand and retrieve the right data, with precision and in context.

While many community and official MCP servers already support connections to major databases like PostgreSQL, MySQL, SQL Server, and more, there's a problem: raw access to data isn't enough.

Enterprises need:

• Accurate semantic understanding of their data models
• Trusted calculations and aggregations in reporting
• Clarity on business terms, like "active customer," "net revenue," or "churn rate"
• User-based permissions and access control

Natural language alone isn't enough to drive complex workflows across enterprise data systems. You need a layer that interprets intent, maps it to the correct data, applies calculations accurately, and ensures security.

🎯 Our Mission

Wren Engine is on a mission to power the future of MCP clients and AI agents through the Model Context Protocol (MCP) — a new open standard that connects LLMs with tools, databases, and enterprise systems.

As part of the MCP ecosystem, Wren Engine provides a semantic engine powered the next generation semantic layer that enables AI agents to access business data with accuracy, context, and governance.

By building the semantic layer directly into MCP clients, such as Claude, Cline, Cursor, etc. Wren Engine empowers AI Agents with precise business context and ensures accurate data interactions across diverse enterprise environments.

We believe the future of enterprise AI lies in context-aware, composable systems. That’s why Wren Engine is designed to be:

• 🔌 Embeddable into any MCP client or AI agentic workflow
• 🔄 Interoperable with modern data stacks (PostgreSQL, MySQL, Snowflake, etc.)
• 🧠 Semantic-first, enabling AI to “understand” your data model and business logic
• 🔐 Governance-ready, respecting roles, access controls, and definitions

With Wren Engine, you can scale AI adoption across teams — not just with better automation, but with better understanding.

Check our full article

🤩 Our Mission - Fueling the Next Wave of AI Agents: Building the Foundation for Future MCP Clients and Enterprise Data Access

🚀 Get Started with MCP

MCP Server README

https://github.com/user-attachments/assets/dab9b50f-70d7-4eb3-8fc8-2ab55dc7d2ec

👉 Blog Post Tutorial: Powering AI-driven workflows with Wren Engine and Zapier via the Model Context Protocol (MCP)

🤔 Concepts

• Powering Semantic SQL for AI Agents with Apache DataFusion
• Quick start with Wren Engine
• What is semantics?
• What is Modeling Definition Language (MDL)?
• Benefits of Wren Engine with LLMs

🚧 Project Status

Wren Engine is currently in the beta version. The project team is actively working on progress and aiming to release new versions at least biweekly.

🛠️ Developer Guides

The project consists of 4 main modules:

1. ibis-server: the Web server of Wren Engine powered by FastAPI and Ibis
2. wren-core: the semantic core written in Rust powered by Apache DataFusion
3. wren-core-py: the Python binding for wren-core
4. mcp-server: the MCP server of Wren Engine powered by MCP Python SDK

⭐️ Community

• Welcome to our Discord server to give us feedback!
• If there is any issues, please visit Github Issues.