Pureinsights Discovery 2.8 Introduces MCP Support for Agentic AI Applications

New enterprise connectors for SharePoint Online, OracleDB, SMB, and LDAP expand out-of-the-box data access for AI pipelines

HERNDON, VA, UNITED STATES, April 8, 2026 /EINPresswire.com/ -- Pureinsights, a leader in AI-powered search and discovery solutions, today announced the release of Discovery 2.8, the latest version of its cloud-native platform for developing and operationalizing intelligent search, assistant, and agent applications. The update delivers a significant expansion of Discovery's integration and automation capabilities, with headline support for the Model Context Protocol (MCP) — positioning the platform at the forefront of the emerging agentic AI landscape.

Discovery 2.8 introduces a broad set of enhancements across ingestion, automation, and query orchestration:

• MCP Support in QueryFlow: Discovery now supports the Model Context Protocol directly within QueryFlow, enabling the creation of custom MCP servers exposed through entrypoints. This opens up a new class of advanced AI and agent use cases, allowing Discovery-powered applications to interoperate seamlessly with the growing ecosystem of MCP-compatible tools and frameworks.

• Schedules API: A new Schedules API in the Ingestion component enables automatic execution of Seeds based on a cron expression, reducing manual intervention and supporting reliable, time-based data pipeline orchestration.

• SharePoint Online Connector: A new SharePoint Online Ingestion Component enables crawling of Sites, Subsites, Lists, and List Items — including the ability to download files and attachments — bringing enterprise document repositories directly into Discovery pipelines.

• OracleDB Connector: Native Oracle Database support is now available, using the Oracle JDBC driver to connect to Oracle databases, execute SQL statements, and retrieve table data for ingestion.

• SMB Connector: Discovery can now connect to SMB servers via a new Filesystem component, enabling crawling of network file shares to extract and ingest their content.

• LDAP Connector: A new LDAP component allows Discovery to run searches against LDAP servers and retrieve users and groups from enterprise directory services.

• Incremental Scanning in Staging: The Staging component now supports incremental scanning using checksum-based identification, improving processing efficiency by avoiding redundant re-ingestion of unchanged content.

• Expression Language — merge() Function: A new merge() function extends Discovery's Expression Language, enabling developers to merge two maps or arrays for more flexible data transformations during ingestion.

"Discovery 2.8 marks an important milestone for the platform — with MCP support, our customers can now connect Discovery directly into the agentic AI workflows and tools they're already building. Combined with our expanded set of enterprise connectors, this release makes it significantly easier for organizations to put their data to work in AI applications," said Kamran Khan, CEO of Pureinsights.

The Pureinsights Discovery Platform provides a low-code, modular environment for orchestrating AI pipelines with real-time configurability. It is used by enterprises to build intelligent search, AI assistant, recommendation, and agent-based applications across industries including financial services, government, retail, and media.

To learn more visit: pureinsights.com/discovery-platform/overview

About Pureinsights

Pureinsights transforms how organizations interact with information through intuitive, human-centered solutions — combining expert services with the power of our Discovery platform. From AI Search and Assistants to intelligent Agents, we help businesses harness Generative AI, Vector Search, and NLP to unlock insights, streamline operations, and spark innovation across use cases ranging from enterprise search to complex, multimodal analysis.

Graham Gillen
Pureinsights Technology Corporation
email us here
Visit us on social media:
LinkedIn
YouTube
X

Legal Disclaimer:

EIN Presswire provides this news content "as is" without warranty of any kind. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.