Suite – DiliTrust MCP Server for Legal AI Use Cases

Modified on Thu, 11 Jun at 3:51 PM

DiliTrust is introducing an MCP (Model Context Protocol) server that enables AI assistants and legal automation tools to connect directly to DiliTrust's platform capabilities. This opens the door to AI-powered legal workflows that go beyond what is possible within the DiliTrust interface alone.


✅ Introduction

The MCP (Model Context Protocol) server is a technical integration layer that allows AI tools — including assistants like those built on large language models — to securely access and interact with DiliTrust's data and features via API. For legal teams that are already exploring AI-powered workflows, this means you can connect DiliTrust to your AI assistant of choice and automate or augment legal tasks using your own data.

Practical examples of what becomes possible include: preparing for a board meeting using AI with access to your documents and past decisions, querying your matter portfolio in natural language from an external AI tool, or building custom legal automation workflows that leverage DiliTrust's API.


✋ Prerequisites / Getting Started

  • The MCP Server feature must be enabled for your organization. Contact your DiliTrust account manager or customer success manager to request access.
  • Your organization must have a technical team (IT or developers) who can configure the OAuth connection between your AI tool and DiliTrust.
  • Access to the DiliTrust developer documentation at developers.dilitrust.com is recommended for technical setup.

⭐ Step-by-Step Guide

Connecting an AI Tool to DiliTrust via MCP

  1. Contact your DiliTrust account manager to have the MCP Server feature enabled for your organization.
  2. Have your IT team review the integration documentation available at developers.dilitrust.com.
  3. Configure the OAuth authentication between your AI tool and DiliTrust's MCP server. This step requires technical setup by your IT or development team.
  4. Once connected, define the business use cases you want to enable (e.g., matter querying, document summarization, meeting preparation).
  5. Test the integration with a non-critical use case before rolling out to your team.

✨ Tips & Best Practices

  • Start with a well-defined use case: Rather than trying to connect everything at once, identify one high-value use case (e.g., meeting prep AI assistant) and build from there.
  • Involve IT early: The OAuth configuration requires technical expertise. Involve your IT team from the start to avoid delays.
  • Review data access permissions: Ensure that the AI tool connecting via MCP only has access to the DiliTrust data it needs for the intended use cases.

❌ Limitations & Known Constraints

  • MCP Server access requires technical setup by your organization's IT team. It is not a plug-and-play feature for end users.
  • OAuth configuration must be completed before the MCP server can be used by external AI tools.
  • Available API routes and data access depend on your DiliTrust subscription and module access.

❓ FAQ

What is an MCP server?

MCP (Model Context Protocol) is a standard that allows AI assistants to securely access external tools and data sources. DiliTrust's MCP server exposes DiliTrust's capabilities via this protocol, enabling AI tools to query and interact with your legal data.

Do I need to be a developer to use this feature?

The initial configuration requires technical setup by a developer or IT professional. Once configured, end users can interact with the connected AI tool as they would normally.

Is my data secure when accessed via MCP?

Yes. Access is controlled via OAuth authentication, and the MCP server only exposes the API routes that have been explicitly enabled. DiliTrust's standard security and data governance policies apply.

Which AI tools are compatible with the DiliTrust MCP server?

Any AI tool or assistant that supports the MCP protocol can connect to DiliTrust's MCP server. Consult your DiliTrust account manager for a list of tested integrations.

Was this article helpful?

That’s Great!

Thank you for your feedback

Sorry! We couldn't be helpful

Thank you for your feedback

Let us know how can we improve this article!

Select at least one of the reasons
CAPTCHA verification is required.

Feedback sent

We appreciate your effort and will try to fix the article