Augment Computing Inc., the maker of an agentic artificial intelligence coding tool for developers, today announced the launch of Model Context Protocol support for its service, which will enable AI coding agents and platforms to use its tools.
Under the hood, the company uses what it calls the Context Engine, a powerful semantic search capability that improves AI understanding of codebases beyond simple static and keyword searches used by large language models and agents.
According to Augment, in its own benchmarks, it has seen improved agentic coding performance of over 70% across Anthropic PBC’s Claude Code, Anysphere Inc.’s Cursor and OpenAI Group PBC’s Codex.
These features allow developers to hook up their favorite AI-powered coding agent platform to write code faster, better and use fewer tokens.
The company explained that every engineering team using AI agents to code faces a similar problem: Agentic AI agents hallucinate and burn tokens on irrelevant context, burning budget on the same mistakes repeatedly. Augment argues that’s because models lack a deep understanding of codebases, architecture, dependencies and patterns.
It’s a common melody sung by every single agentic coding platform released over the past year. Every month, another startup and enterprise vendor has offered new benchmarks showing better performance numbers to entice developers to try products.
Model Context Protocol allows Augment’s agents to connect to independent developer environments, command line interfaces, large language models and other agents.
The company said it can deliver between 30% to 80% in quality improvements. In Cursor + Claude Opus 4.5, it displayed a 71% improvement, Claude Code + Opus 4.5 received an 80% improvement, and Cursor + Composer-1 saw a 30% improvement.
The company explained that with the Context Engine, users can align themselves with a less powerful model – for example, Sonnet versus Opus – and it will outperform a larger model with poor context. That’s because provisioning high-quality context will always deliver better code.
At the core of Augment’s argument is that this reduces the total amount of search failures that happen. By delivering a deeper semantic understanding of code, better known as accuracy and selectivity, the company says that the engine can deliver what’s needed for the task while avoiding what’s not. This reduces costs and speeds up operations – it also provides comprehension of relationships, dependencies and the underlying architecture.
The addition of MCP enables the integration with any MCP-compatible platform, LLM and agent using the open protocol starting today.
Image: News/Microsoft Designer, Augment
Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.
- 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more
- 11.4k+ theCUBE alumni — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network.
About News Media
Founded by tech visionaries John Furrier and Dave Vellante, News Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.
