The affordability calculator will be available to large language models (LLMs), which use MCPs to connect to external data tools and sources in a standardised way.
MPowered said this would result in a “significant shift” in how consumers and machines interact with financial products online.
The firm claimed that as AI personal assistants are more frequently used on the internet, websites are being increasingly visited by LLMs. The LLMs query data, interpret context and return answers to users in natural language.
Jake Atkinson, director of growth at MPowered, said: “We’re not just optimising for mobile or web anymore, we’re actively building for an LLM-first internet.
“This is about making sure that when your AI assistant goes looking for mortgage information, it can talk directly to the source. Safely, accurately, and in context”.
Why new-build property investment is appealing to a new generation of landlords
Sponsored by BM Solutions
Through this update, MPowered has made its lending criteria available to LLMs, allowing AI agents to interact with the calculator in real time and return personalised borrowing estimates. MPowered said this would reduce reliance on static websites and outdated third-party summaries.
Stelios Constantinidis, director of AI at MPowered, added: “The MCP is rapidly becoming the standard for how models safely interface with live, trusted data sources”.
The lender said this development set a “new precedent” for financial institutions when using AI while maintaining control over data integrity and context.
The update was developed in partnership with MPowered’s parent company, MQube Technology.
MPowered said this was the first of a number of MCP integrations it was planning to launch in an effort to redefine the mortgage experience through AI and automation.
