> For the complete documentation index, see [llms.txt](https://cortex-docs.paloaltonetworks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://cortex-docs.paloaltonetworks.com/cortex-cloud-posture-management/onboard-and-configure/post-deployment-steps/cortex-mcp-server/create-custom-cortex-mcp-server-tools.md).

# Create custom Cortex MCP server tools

Create custom tools for the Cortex MCP server.

You can build your own tools using OpenAPI or Python to manage cases, handle issues, and conduct investigations. More detailed information can be found in the README file located in the `src/usecase` directory. Tools are based on Cortex API endpoints.

To view the Cortex Cloud API documentation, see [Cortex Cloud APIs](https://cortex-docs.paloaltonetworks.com/cortex-cloud-api/).

Any new or updated components provided by Cortex are automatically downloaded into the builtin\_components folder. During each update, the folder is fully replaced and all existing contents are recreated. Do not add custom tools to this directory, as it is managed entirely by Cortex and is overwritten at every update.

**OpenAPI**

You can create an OpenAPI specification for a specific API endpoint.

1. Create a YAML file in the `/custom_components/openapi` directory with the name of the MCP component. For example: `custom_cortex_component.yaml`.
2. Base your custom OpenAPI component on the Cortex API documentation structure for a specific endpoint. We recommend viewing the built-in tools, located at `/builtin_components/openapi`, as a reference.
3. After you define the OpenAPI specification, the Cortex MCP server collects it automatically and it is ready for use.
4. Test your new MCP component by running the Cortex MCP server and writing a prompt that uses your new component.

**Python**

We recommend using Python for more complex MCP components that require custom logic. MCP components in Python are defined in a module.

1. Create a new Python file in the `/custom_components` directory.
2. Define a class that inherits from the `BaseModule` class with the required methods. We recommend viewing the built-in modules, located at `/builtin_components`, as a reference.
3. After you define a class, the Cortex MCP server collects it automatically and it is ready for use.
4. Test your new MCP component by adding an end-to-end test in the `tests/e2e` directory or run the MCP server and write a prompt that uses your new component.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://cortex-docs.paloaltonetworks.com/cortex-cloud-posture-management/onboard-and-configure/post-deployment-steps/cortex-mcp-server/create-custom-cortex-mcp-server-tools.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.