> For the complete documentation index, see [llms.txt](https://developers.epiqai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developers.epiqai.com/about-epiq-ai-mcp.md). # About Epiq AI MCP Epiq AI is Epiq's platform for case-centered legal data analysis, document search, entity review, and project workflows. Epiq AI MCP brings a focused read-only slice of that platform into Claude. Instead of switching between Epiq AI screens to find the right project, collection, or document evidence, a user can ask Claude in plain English. Claude calls the Epiq AI MCP server on the user's behalf and returns answers grounded in Epiq AI data, scoped to the active Epiq AI account and the user's project permissions. ### What it does The connector allows Claude to retrieve information from Epiq AI so you can: * Find your projects (cases/matters) * Explore document collections within a project * Search documents and return relevant excerpts * Identify people and organizations (entities) * Summarize findings using evidence from your data Claude always works from your actual case documents and includes source material in its responses. ### What it is, technically Epiq AI MCP is a Remote MCP server implemented with the official MCP Python SDK's FastMCP server. It uses Streamable HTTP transport at the server root path, OAuth protected-resource metadata for discovery, and Okta-issued bearer tokens for authentication. The current connector surface is intentionally narrow and read-only: account selection plus four project, collection, and search tools. ### Who it is for * Litigation teams that need quick project and collection discovery. * Attorneys and review leads who need document-search evidence from Epiq AI without leaving their assistant. * Case teams looking for people, organizations, and other entities mentioned in case documents. * Epiq AI administrators validating a low-risk remote MCP connector before expanding the tool surface. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://developers.epiqai.com/about-epiq-ai-mcp.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.