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

# Claude

## Connection

Connections provide secure access to the integrated app that you use in a MESA workflow. Your Claude connection securely links your workflows with your Anthropic account.

When you're setting up your first workflow with Claude, you'll need to create an Anthropic API Key.

<figure><img src="https://3425906282-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1H6u1HQc3Iew7ATmmiCi%2Fuploads%2FWLveDEZHyQI06v4Bsyus%2Fimage.png?alt=media&amp;token=7a596c97-4281-4081-b58e-814817da9b3a" alt="Screenshot of the MESA Claude step connection setup, linking your workflow with your Anthropic account. Spotlight the API Key credential field."><figcaption></figcaption></figure>

To find your Anthropic API Key, go to: <https://console.anthropic.com/settings/keys>. Click the Create Key button and name your key (e.g. MESA).

<figure><img src="https://3425906282-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1H6u1HQc3Iew7ATmmiCi%2Fuploads%2FKRzMDhiF6Hb0FsotVAEY%2Fimage.png?alt=media&amp;token=01ca36b6-3ab6-4190-99c8-1e15a542fb5d" alt="Screenshot of the Anthropic Console API Keys settings page where you name the key MESA. Spotlight the Create Key button."><figcaption></figcaption></figure>

Click the Copy Key from the pop-up that appears. Once you obtain your API key, you can paste the API key into your workflow connection's API Key field.

<figure><img src="https://3425906282-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1H6u1HQc3Iew7ATmmiCi%2Fuploads%2FDsp6KiQqws53Bldx0ie3%2Fimage.png?alt=media&amp;token=339d8f34-dfaf-4673-9a9d-3b34a28fd879" alt="Screenshot of the Anthropic Console API key created pop-up. Spotlight the Copy Key button."><figcaption></figcaption></figure>

## Configure <a href="#configuring" id="configuring"></a>

#### Following Anthropic's Usage Policies <a href="#policy" id="policy"></a>

Please ensure that you follow Anthropic's Usage Policies when using MESA's Claude integration: <https://www.anthropic.com/legal/aup>

#### ShopPad's Recommendation <a href="#recommendation" id="recommendation"></a>

We recommend testing the prompt in the Anthropic dashboard before using MESA's Create Message action. This allows you to try different models and prompts and will estimate the token cost for each automation.

As Claude is not our product, we would like to note that we are not responsible for its output. We recommend replicating your preferred prompt using the Claude UI to verify that it meets your expectations before automating it with MESA.

## How Claude Uses Your Data <a href="#data-security" id="data-security"></a>

The Claude app makes API calls to Anthropic. Only the variables explicitly configured in the MESA builder will be shared with Anthropic. MESA does not store any of this information beyond your data retention date. Anthropic does not use data submitted to and generated by their API to train Anthropic models or improve Anthropic's service offering.

To opt out of any data sharing with AI models, simply do not use the Claude step in any of your workflows.

[Learn more](https://support.anthropic.com/en/articles/7996885-how-do-you-use-personal-data-in-model-training) about how and when Anthropic uses use to train their models. Read [MESA's Data Processing Agreement](https://www.getmesa.com/dpa).


---

# 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://docs.getmesa.com/connect/claude.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.
