> For the complete documentation index, see [llms.txt](https://docs.panther.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.panther.com/ai/mcp.md).

# MCP

Panther exposes a [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server so MCP clients — editors, chat tools, scripted agents — can use Panther's tools through natural language. Ask about alerts, query the data lake, look up an indicator, pull a detection's source, and more, all from your client of choice.

There are two ways to connect:

* [**Panther Remote MCP**](https://docs.panther.com/~/revisions/i7lJ3BCO5BWSo8qHQtoL/ai/panther-mcp-server)— the hosted endpoint at your Panther instance. OAuth-based sign-in, per-connection consent, and consolidated audit logging. Recommended for most users.
* [**Local MCP** ](/ai/mcp/mcp-server.md)— the open-source [`mcp-panther`](https://github.com/panther-labs/mcp-panther) package, installed via `docker` or `uvx` and authenticated with a Panther API token. Useful for CI pipelines, scripted agents, and custom internal tooling.

{% hint style="info" %}
Use of Panther MCP features is subject to the [AI disclaimer found on the Legal page](https://docs.panther.com/resources/help/legal#ai-disclaimer).
{% endhint %}

{% content-ref url="/pages/KTENRwMIBKNcm4zIVuww" %}
[MCP Integrations (Beta)](/ai/mcp/mcp-integrations.md)
{% endcontent-ref %}


---

# 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:

```
GET https://docs.panther.com/ai/mcp.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.