MCP server for Apache Wayang

Are you interested in working with a big data open source project and AI?

You are welcome to conduct your thesis/project in the context of Apache Wayang. Apache Wayang is the first cross-platform framework that allows users to specify their task/query in a system-agnostic manner and Wayang will determine which is the best system(s) to execute this task with the goal of optimizing performance. For a general overview check this paper. This project aims to implement an Model Context Protocol (MCP) server for Apache Wayang. MCP is an open protocol that standardizes how applications provide context to LLMs (https://modelcontextprotocol.io/).
In this way, agentic architectures will be able to use Wayang to access to locally stored private data and do some analysis to extract insights on the data before handling this information to the LLMs.

Intended Learning Outcomes:

• Ability to contribute to large open source codebases
• Ability to reason about protocols for agent communication

Prerequisites: good programming skills in Python; (good but not necessary to have) knowledge in agentic architectures and in big data systems (e.g., Apache Flink, Apache Spark).