> 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/use-epiq-ai-mcp.md).

# Use Epiq AI MCP

After the connector is set up, you can ask Claude questions about your Epiq AI projects in natural language.

Ask questions in plain English.

You do not need to know a specific query syntax to begin.

You can ask about:

* Projects (matters)
* Document content
* Metadata
* Entities (people or organizations)
* Themes, issues, or case-specific questions

### Example prompts

#### Find and summarize information

* “Summarize this project.”
* “What are the main issues discussed in these documents?”
* “Give me a high-level overview of this matter.”

#### Locate references

* “Which documents mention \[person or company name]?”
* “Find documents related to this contract issue.”
* “What content references the merger timeline?”

#### Explore patterns and details

* “What are the most common entities in this dataset?”
* “What topics appear most frequently in these documents?”
* “What can you tell me about communications involving \[person]?”

#### Compare or drill down

* “How do these two document groups differ?”
* “What is the timeline of events reflected in these documents?”
* “Which documents appear most relevant to this issue?”

### Best practices

For the best results:

* Start broad, then refine
* Reference specific projects, document groups, or concepts when possible
* Use follow-up prompts to clarify or narrow the result
* Validate high-impact findings in Epiq AI when needed for downstream actions

### When to use Epiq AI directly

Use Claude for exploration and summarization.

Use Epiq AI directly when you need to:

* Review documents in detail
* Apply coding or decisions
* Update metadata or project settings
* Perform operational workflows that require system actions


---

# 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/use-epiq-ai-mcp.md?ask=<question>&goal=<endgoal>
```

`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.