Kurrent has introduced its open source MCP Server, a tool designed to simplify how developers and AI agents interact with databases. Built for use with KurrentDB, the platform allows users to query, write, and test event streams and projections using natural language—no code required.
This release represents a step forward in enabling AI-native workflows in software development. Instead of requiring SQL or scripting knowledge, developers can now work with databases through simple prompts. That includes reading and writing data, building projection logic, and debugging—all from a conversational interface.
The MCP Server is compatible with leading frontier AI models such as GPT-4, Claude, and Gemini, and works with a range of developer tools including Windsurf and Cursor. It is released under the MIT license, allowing free use, modification, and contribution from the broader open source community.
Our new MCP Server makes it possible to use the main features of the KurrentDB database, like reading and writing events to streams and using projections, in a way that’s as simple as having a conversation. The system’s ability to test and fix itself reduces the need for debugging and increases reliability. Copilots and AI assistants become productive database partners rather than just code generators, seamlessly interfacing with KurrentDB.”
Kirk Dunn, CEO at Kurrent
Kurrent’s goal is to remove friction from the database development process by making core data tasks conversational and intuitive. For developers and AI systems alike, the ability to read, write, and validate projections using natural language unlocks a faster path to experimentation and application prototyping.
The tool includes eight built-in commands:
- Read_stream – query streams for specific data
- List_streams – view available streams in the database
- Build_projection – generate code based on prompts
- Create_projection – deploy new projections in real time
- Update_projection – modify existing logic
- Test_projection – validate projection behavior with sample data
- Write_events_to_stream – log events directly
- Get_projections_status – check projection health and debug
One of the MCP Server’s most unique features is self-correction. When a projection doesn’t behave as expected, the system can automatically identify and help fix logic errors through follow-up prompts, reducing manual debugging.
The server is designed to work with all AI assistants that follow the Model Context Protocol (MCP), meaning it can be integrated into a growing range of tools, frameworks, and workflows. This opens the door to agent-based systems that not only generate code but take full responsibility for implementing, testing, and refining application logic.
According to the team behind the tool, the long-term vision is to enable AI agents to become full partners in data management—handling infrastructure tasks, running analytical routines, and surfacing insights without human micromanagement.
Kurrent is encouraging community participation through GitHub and has made clear documentation and onboarding materials available for those interested in customizing or extending the server. Developers are invited to contribute new features, request improvements, and help shape the direction of the project.
The MCP Server aligns with Kurrent’s broader strategy to position its event-native data platform as the foundation for real-time, agent-driven data experiences. KurrentDB already powers use cases in finance, manufacturing, healthcare, and energy, and the company sees AI-enabled access as a natural extension of that mission.
Learn how AI Agents can supercharge your company’s profits and productivity at TMC’s AI Agent Event in Sept 29-30, 2025 in DC.
Aside from his role as CEO of TMC and chairman of ITEXPO #TECHSUPERSHOW Feb 10-12, 2026, Rich Tehrani is CEO of RT Advisors and a Registered Representative (investment banker) with and offering securities through Four Points Capital Partners LLC (Four Points) (Member FINRA/SIPC). He handles capital/debt raises as well as M&A. RT Advisors is not owned by Four Points.
The above is not an endorsement or recommendation to buy/sell any security or sector mentioned. No companies mentioned above are current or past clients of RT Advisors.
The views and opinions expressed above are those of the participants. While believed to be reliable, the information has not been independently verified for accuracy. Any broad, general statements made herein are provided for context only and should not be construed as exhaustive or universally applicable.
Portions of this article may have been developed with the assistance of artificial intelligence, which may have contributed to ideation, content generation, factual review, or editing.
Media News Article: https://blog.tmcnet.com/blog/rich-tehrani/ai/kurrent-launches-open-source-mcp-server-to-enable-ai-native-code-free-database-interaction.html