Lexsoft T3 Gains MCP Integration and OpenAI Vector Indexer for Legal Workflows

May 19, 2026
Lexsoft Systems has made its legal knowledge management system, T3, fully accessible through the Model Context Protocol and added a Microsoft-based OpenAI vectorized Indexer for semantic search, enabling deeper integration with AI tools such as Copilot, Claude, Gemini, and Harvey.

Lexsoft announced in a press release that its legal knowledge management system, Lexsoft T3, is now fully accessible via the Model Context Protocol. The update allows law firms and corporate legal departments to connect T3 with MCP compatible legal AI orchestrators, including Microsoft Copilot, Claude, and Gemini, as well as third party platforms such as Harvey.

The company also introduced a new Microsoft based OpenAI vectorized Indexer in T3 that supports semantic searching. This Indexer enables context aware results by understanding the meaning of search terms and their usage, distinguishing between similar words in different contexts. The Indexer operates within an organization's own OpenAI tenant in the Microsoft environment to maintain data security and residency compliance.

These capabilities move T3 from a standalone knowledge management system to a component of orchestrated AI legal workflows. With T3 as a curated knowledge source, AI tools can extract verified information with contextual references, improving the reliability of AI assisted legal research and document classification.

Organizations using T3 can choose to retain their current Indexer or switch to the new vectorized version for enhanced semantic search performance.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Legal AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Legal AI AI Brief AI Brief (X)
Free newsletter

Legal AI Weekly

The source for the Legal AI software news, analysis, emerging applications: contract review, e-discovery, research.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.