VIDIZMO integration brief · Relativity · vidizmo.ai/integrations/catalog/relativity

Integrations / Relativity

Relativity

Exchange review sets, and let a workflow work them. Visit website

Relativity is the dominant ediscovery platform for large-scale document and data review.

Media and metadata move both ways, so audio and video are transcribed and redacted where that is done well and reviewed in Relativity with the documents. A workflow runs first-pass review over the transcripts, surfacing responsive material and flagging likely privilege for a lawyer to confirm.

A First Pass Over the Recordings Before Review Begins

Open as a two-page brief

Relativity is where large-scale document review happens, and audio and video are the part of a collection it handles least comfortably. Transcription, redaction and playback are done well elsewhere, and the review still has to account for them. Relativity runs an official MCP server, and AI Intelligence Hub connects to MCP servers as a client, so a workflow works against a workspace with configuration rather than development. Relativity stays the review platform.

How it connects

Relativity's MCP server is reached as a client. The connection is configured once with a name, the server URL, the transport and the HTTP headers carrying its credential, and the server's tool list is fetched when the connection binds rather than coded in. A workflow uses an MCP node to run one named tool with arguments fixed at design time; an agent is handed the tool list and chooses as it works. Where a step needs something the server does not expose, the HTTP Request node calls Relativity's own API, and in the other direction the platform's REST API and a workflow's HTTP trigger let automation on the Relativity side start a workflow.

The connection carries the credential it is configured with, so what it can read or change in a workspace is bounded by what that credential is granted there. Where a first-pass review runs over material held in the library, retrieval runs under the asking user's identity with their access list pre-filtered into the query.

Moving media and its metadata between the library and a Relativity workspace is a separate piece of work, scoped per engagement against the published APIs on both sides rather than prebuilt.

What you can do together

  • Have audio and video transcribed in the library and redacted in Redactor, so recordings reach reviewers searchable and with personal data removed while the documents are reviewed in Relativity.
  • Run a first pass over transcripts in a workflow, surfacing responsive passages and flagging likely privilege for a lawyer to confirm rather than deciding anything.
  • Work a workspace from a workflow through the tools Relativity's MCP server exposes, without an integration built for each task.
  • Trigger a workflow from the Relativity side when a batch lands, so processing starts without anyone watching a queue.

A scenario

  1. SetupAn administrator adds Relativity's MCP server with a credential scoped to the matter's workspace. The tool list appears without development.
  2. ProcessingThe recordings are transcribed in the library, and personal data that must not reach reviewers is redacted in Redactor.
  3. First passA workflow reads the transcripts, marks passages responsive to the agreed terms, and flags candidates for privilege. Nothing is coded as a decision; each is a suggestion for a reviewer.
  4. ReviewReviewers work the documents in Relativity as usual, and open the flagged transcripts and redacted recordings in the library under their own access.
  5. ReportingA partner asks for the state of the review. The agent reads the workspace through Relativity's server and answers from it.

What stays where

Relativity remains the review platform

Workspaces, coding, batching and the review record stay there, and nothing about the workflow changes how reviewers work.

The credential is the boundary on the Relativity side

What the connection can read or change is what its configured credential is granted, so scoping it per matter is the control.

Media governance stays in the library

Transcripts, redactions, access rules, retention and the custody record live in the platform, and retrieval from it runs as the asking user.

Processing runs where you deploy the platform

Shared or dedicated SaaS, your own cloud subscription, or your own servers. Reaching a hosted Relativity workspace needs a network path to it.

Products and solutions

Next step

See it on your own Relativity instance. We will show the connection made, the data moving and the output, then size it for your deployment.

Request a demonstration  or write to sales@vidizmo.ai

sales@vidizmo.ai  ·  vidizmo.ai/integrations/catalog/relativity

Not what you need?

We build it

Send us your API documentation and we build, test and maintain the connector, at no development cost to you.

Request this integration

Bring an MCP server

If the system publishes a Model Context Protocol server, AI Intelligence Hub connects to it as a client with configuration alone.

Define a REST endpoint

Describe your endpoint and it becomes a node in an agent workflow, without waiting on our roadmap.

Product names, logos and trademarks shown here are the property of their respective owners. Their use does not imply any affiliation with or endorsement by them.