Toffee
Project Toffee aims to develop a comprehensive suite of MCP tools tailored for AI-driven software engineering
Toffee
Toffee
Project Toffee aims to develop a comprehensive suite of MCP tools tailored for AI-driven software engineering
Project Overview
In the rapidly evolving landscape of software engineering, Large Language Models are transforming the way we approach automation. However, the effectiveness of LLM-driven solutions hinges on one critical factor: the quality of context provided to the model. Without rich, precise, and relevant context, even the most advanced LLMs can fall short in delivering meaningful results.
Project Toffee is dedicated to bridging this gap by developing a comprehensive suite of MCP tools tailored for software engineering tasks. These tools are designed to be seamlessly integrated with AI agents, enabling them to perform complex engineering tasks with greater accuracy and efficiency.
Our MCP tools are specialized modules that extract, generate, and refine the contextual information required for various software engineering activities by combining program analysis with LLMs. By converting these tools into discoverable MCP servers, we enable AI agents to dynamically access and utilize the right tool for the right task—whether it’s bug triaging, repairing code, generating tests, completing code snippets, or configuring software systems
Mahin Chandramohan is leading AI/ML initiatives in the Intelligent Application Security Group at Oracle Labs, Australia.
His research interests include:
• Automated program repair (APR)
• Large language models (LLMs)
• Open Source Intelligence (OSINT)
• Threat intelligence
• Malware analysis and binary reverse engineering
• Machine learning for program analysis and bug detection (MLonCode)
Education:
• PhD in Computer Science, Nanyang Technological University, Singapore
• B.Eng. in Computer Engineering, Nanyang Technological University, Singapore