We built an MCP server that lets AI call the Understand API instead of guessing about code. This article walks through the design choices, implementation, and setup required to make that work in practice.
Tag: api
Engineer versus AI Script Writing Contest
Abstract: a comparison of writing a plugin script by hand versus using AI. After immense pressure, I try using Cursor to write a plugin script to list the nodes and edges in a Shared Tasks Graph. Using AI turned out to be a bit faster and was a lot less painful than I’d imagined.
What Happens When You Teach ChatGPT the Understand API?
We built a custom ChatGPT assistant to help users write and debug scripts using the Understand Python API, making Understand’s power more accessible and efficient.
Custom Charts in Understand 7.0
Understand 7.0 makes it easier for users to create custom charts. With new tools and a redesigned Plugin Manager, developers can change existing charts or make new ones to fit their needs. This gives users more flexibility when analyzing and presenting their code.
Interactive Reports in Understand 7.0
Understand 7.0 introduces powerful new features to Interactive Reports (IReports), enabling users to generate dynamic reports with tables, charts, and customizable formatting. These enhancements streamline workflow and allow for easy sharing of reports via HTML and PDF exports.
Finding Shared Global Objects
Having problems with threading? Check out these plugins to identify shared global objects. The plugins also use a cool trick: architectures as entity tags to store information like thread priorities.
Duplicate Lines of Code
Revisiting how we detect and report duplicate lines of code, and creating a plugin metric to report it.
Overly Complex Files
Frustrated by vague code quality metrics? Explore how to translate CBR Insight’s metrics for file complexity, thresholds, and comment to code ratio into equivalent custom Understand metrics to gain a more nuanced understanding of your code’s quality.
Cognitive Complexity Metric Plugin
A detailed technical description of how to calculate cognitive complexity using Understand’s API and why the cognitive complexity metric could be important to you.
Custom Report: Finding Parameter Values
Understand’s Python API makes it a great platform for creating quick tools to explore exactly what you are interested in. In this case, I was curious if a default parameter was ever set to a non-default value or if a given parameter is always the same value. Check out these two custom interactive reports that show parameter values for each call.