> ## Documentation Index
> Fetch the complete documentation index at: https://docs-xcor.paloaltonetworks.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Cortex XCOR MCP server

> Learn how to connect large language models to the Cortex XCOR MCP server.

Connect large language models (LLMs) to Palo Alto Networks Cortex XCOR using
the Model Context Protocol (MCP) server. After connecting, your LLM can:

* Query [telemetry data](/overview/types) including change events, metrics, logs, and
  traces.
* Read [Cortex XCOR resources](/integrate/mcp-server/resources), such as dashboards
  and monitors.
* Search and retrieve Cortex XCOR documentation through the
  [documentation MCP server](https://docs.chronosphere.io/mcp).

<Note>
  The Cortex XCOR MCP server is read-only. It doesn't support mutation actions such
  as updating dashboards, writing metrics and logs, or deleting monitors.
</Note>

Use AI-enabled developer tools such as [Claude Code](https://www.claude.com/product/claude-code),
[Cursor](https://cursor.com/home?from=agents),
[Codex](https://developers.openai.com/codex/mcp/),
and [Gemini](https://github.com/google-gemini/gemini-cli/tree/main) to submit queries.
Example use cases:

* Find error logs with stack traces and review code for root cause analysis.
* Fetch a monitor's configuration and explain what's triggering it.
* Write PromQL queries targeting a specific service's metrics.
* List active shaping rules, such as drop rules, to determine why data is or isn't
  being dropped.

## Get started

To get started with the Cortex XCOR MCP server,
[configure authentication](/integrate/mcp-server/authenticate).


## Related topics

- [Integrate with Cortex XCOR](/integrate.md)
- [Authenticate with the Cortex XCOR MCP server](/integrate/mcp-server/authenticate.md)
- [Cortex XCOR MCP server tools](/integrate/mcp-server/resources.md)
- [Get started with Cortex XCOR](/overview/get-started.md)
- [Ask Operator about your telemetry](/navigate/operator.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.