Wren Engine

1<p align="center">
2  <a href="https://getwren.ai">
3    <picture>
4      <source media="(prefers-color-scheme: light)" srcset="./misc/wrenai_logo.png">
5      <img src="./misc/wrenai_logo.png">
6    </picture>
7    <h1 align="center">Wren Engine</h1>
8  </a>
9</p>
10 
11<p align="center">
12  <a aria-label="Follow us" href="https://x.com/getwrenai">
13    <img alt="" src="https://img.shields.io/badge/-@getwrenai-blue?style=for-the-badge&logo=x&logoColor=white&labelColor=gray&logoWidth=20">
14  </a>
15  <a aria-label="License" href="https://github.com/Canner/wren-engine/blob/main/LICENSE">
16    <img alt="" src="https://img.shields.io/github/license/canner/wren-engine?color=blue&style=for-the-badge">
17  </a>
18  <a aria-label="Join the community on GitHub" href="https://discord.gg/5DvshJqG8Z">
19    <img alt="" src="https://img.shields.io/badge/-JOIN%20THE%20COMMUNITY-blue?style=for-the-badge&logo=discord&logoColor=white&labelColor=grey&logoWidth=20">
20  </a>
21  <a aria-label="Canner" href="https://cannerdata.com/">
22    <img src="https://img.shields.io/badge/%F0%9F%A7%A1-Made%20by%20Canner-blue?style=for-the-badge">
23  </a>
24</p>
25 
26> Wren Engine is the Semantic Engine for MCP Clients and AI Agents. 
27> [Wren AI](https://github.com/Canner/WrenAI) GenBI AI Agent is based on Wren Engine.
28 
29<img src="./misc/wren_engine_overview.png">
30 
31## 🔌 Supported Data Sources
32- [BigQuery](https://docs.getwren.ai/oss/wren_engine_api#tag/BigQueryProjectConnectionInfo)
33- [Google Cloud Storage](https://docs.getwren.ai/oss/wren_engine_api#tag/GcsFileConnectionInfo)
34- [Local Files](https://docs.getwren.ai/oss/wren_engine_api#tag/LocalFileConnectionInfo)
35- [MS SQL Server](https://docs.getwren.ai/oss/wren_engine_api#tag/MSSqlConnectionInfo)
36- [Minio](https://docs.getwren.ai/oss/wren_engine_api#tag/MinioFileConnectionInfo)
37- [MySQL Server](https://docs.getwren.ai/oss/wren_engine_api#tag/MySqlConnectionInfo)
38- [Oracle Server](https://docs.getwren.ai/oss/wren_engine_api#tag/OracleConnectionInfo)
39- [PostgreSQL Server](https://docs.getwren.ai/oss/wren_engine_api#tag/PostgresConnectionInfo)
40- [Amazon S3](https://docs.getwren.ai/oss/wren_engine_api#tag/S3FileConnectionInfo)
41- [Snowflake](https://docs.getwren.ai/oss/wren_engine_api#tag/SnowflakeConnectionInfo)
42- [Trino](https://docs.getwren.ai/oss/wren_engine_api#tag/TrinoConnectionInfo)
43- [Athena](https://docs.getwren.ai/oss/wren_engine_api#tag/AthenaConnectionInfo)
44- [Databricks](https://docs.getwren.ai/oss/wren_engine_api#tag/DatabricksTokenConnectionInfo)
45- [Redshift](https://docs.getwren.ai/oss/wren_engine_api#tag/RedshiftConnectionInfo)
46- [Apache Spark](https://docs.getwren.ai/oss/wren_engine_api#tag/SparkConnectionInfo)
47 
48## 😫 Challenge Today
49 
50At 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**.
51 
52While 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**.
53 
54Enterprises need:
55- Accurate semantic understanding of their data models
56- Trusted calculations and aggregations in reporting
57- Clarity on business terms, like "active customer," "net revenue," or "churn rate"
58- User-based permissions and access control
59 
60<p align="center">
61  <img width="920" height="638" alt="without_wren_engine" src="https://github.com/user-attachments/assets/3295dde5-ce41-4e56-a8ad-daff6a0c3459" />
62</p>
63 
64Natural 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.
65 
66## 🎯 Our Mission
67 
68Wren 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.
69 
70As 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. 
71 
72By 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.
73 
74We believe the future of enterprise AI lies in **context-aware, composable systems**. That’s why Wren Engine is designed to be:
75 
76- 🔌 **Embeddable** into any MCP client or AI agentic workflow
77- 🔄 **Interoperable** with modern data stacks (PostgreSQL, MySQL, Snowflake, etc.)
78- 🧠 **Semantic-first**, enabling AI to “understand” your data model and business logic
79- 🔐 **Governance-ready**, respecting roles, access controls, and definitions
80 
81<p align="center">
82  <img width="1267" height="705" alt="with_wren_engine" src="https://github.com/user-attachments/assets/3a6531fe-4731-4f21-ae9a-786b219f3c0e" />
83</p>
84 
85With Wren Engine, you can scale AI adoption across teams — not just with better automation, but with better understanding.
86 
87***Check our full article***
88 
89🤩 [Our Mission - Fueling the Next Wave of AI Agents: Building the Foundation for Future MCP Clients and Enterprise Data Access](https://getwren.ai/post/fueling-the-next-wave-of-ai-agents-building-the-foundation-for-future-mcp-clients-and-enterprise-data-access)
90 
91## 🚀 Get Started with MCP 
92[MCP Server README](mcp-server/README.md)
93 
94https://github.com/user-attachments/assets/dab9b50f-70d7-4eb3-8fc8-2ab55dc7d2ec
95 
96 
97👉 Blog Post Tutorial: [Powering AI-driven workflows with Wren Engine and Zapier via the Model Context Protocol (MCP)](https://getwren.ai/post/powering-ai-driven-workflows-with-wren-engine-and-zapier-via-the-model-context-protocol-mcp?utm_campaign=10904457-MCP&utm_content=330804773&utm_medium=social&utm_source=linkedin&hss_channel=lcp-89794921)
98 
99## 🤔 Concepts
100 
101- [Powering Semantic SQL for AI Agents with Apache DataFusion](https://getwren.ai/post/powering-semantic-sql-for-ai-agents-with-apache-datafusion)
102- [Quick start with Wren Engine](https://docs.getwren.ai/oss/engine/get_started/quickstart)
103- [What is semantics?](https://docs.getwren.ai/oss/engine/concept/what_is_semantics)
104- [What is Modeling Definition Language (MDL)?](https://docs.getwren.ai/oss/engine/concept/what_is_mdl)
105- [Benefits of Wren Engine with LLMs](https://docs.getwren.ai/oss/engine/concept/benefits_llm)
106 
107## 🚧 Project Status
108Wren Engine is currently in the beta version. The project team is actively working on progress and aiming to release new versions at least biweekly.
109 
110## 🛠️ Developer Guides
111The project consists of 4 main modules:
1121. [ibis-server](./ibis-server/): the Web server of Wren Engine powered by FastAPI and Ibis
1132. [wren-core](./wren-core): the semantic core written in Rust powered by [Apache DataFusion](https://github.com/apache/datafusion)
1143. [wren-core-py](./wren-core-py): the Python binding for wren-core
1154. [mcp-server](./mcp-server/): the MCP server of Wren Engine powered by [MCP Python SDK](https://github.com/modelcontextprotocol/python-sdk)
116 
117## ⭐️ Community
118 
119- Welcome to our [Discord server](https://discord.gg/5DvshJqG8Z) to give us feedback!
120- If there is any issues, please visit [Github Issues](https://github.com/Canner/wren-engine/issues).
121 
122