Smarsh Adds MCP Server and AskSmarsh AI

Smarsh, a provider of digital communications data and intelligence, has expanded its Communications Intelligence Platform with a Model Context Protocol (MCP) Server, a conversational AI intelligence layer called AskSmarsh AI, and expanded agentic capabilities.

With these system upgrades, companies can now unify work streams, build their own governed data and AI environments, and access Smarsh intelligence directly inside the tools their teams and AI agents already use.

"AI changes the model," said Kamesh Tumsi, chief product officer of Smarsh, in a statement." Customers will be able to use AskSmarsh AI to interact with their communications data conversationally, build on top of us, or bring governed Smarsh intelligence into the tools they already use. We're building for the challenges our customers face today while giving them the openness, intelligence, and flexibility to adapt to what comes next."

The Smarsh MCP Server gives organizations a secureconnection between their AI tools and Smarsh's communications intelligence data, so compliance teams can query the archive, surface insights, and trigger workflows. Every interaction is subject to the same role-based access controls (RBAC), audit logging, and chain-of-custody requirements.

AskSmarsh AI gives users a single, natural-language entry point to search, investigate, report, and act on communications data. Behind the scenes, specialized Search, Reporting, and Export Agents handle the heavy lifting.

Smarsh is also rolling out the following purpose-built agents across the platform:

• MySearch Agent, which gives employees secure, self-service access to their own archived communications across email, chat, voice, mobile, and social.
• Discovery Agent, which adds deeper legal research across financial misconduct, non-financial misconduct, and employment discrimination using Smarsh's Semantic Context Graph.
• Intelligent Agent, which adds three Non-Financial Misconduct Models: Hostile, Abusive, and Discriminatory Language, Sexual Harassment, and Intent to Resign.

And new capture integrations with Claude Enterprise, Amazon Bedrock, and Google Workspace help extend Smarsh's governed data foundation to emerging AI and communications surfaces.