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

# Anthropic Claude

https\://platform.claude.com

The Anthropic Claude connector (*AI* > *Anthropic Claude*: *AI Agent*, *Send Prompt*, *Transform Text to JSON*, *List Models*, *Make API Call*) authenticates with an Anthropic API key. Each user enters their own key when connecting an account in the Designer, so there is no app to register with Anthropic.

## Get an API key

1. Sign in to the Claude Console at [platform.claude.com](https://platform.claude.com) (formerly console.anthropic.com). Create an account if you do not have one.
2. Open *Settings* > *API keys* ([platform.claude.com/settings/keys](https://platform.claude.com/settings/keys)).
3. Click *Create Key*, give the key a name and select the workspace it belongs to.
4. Copy the key (it starts with `sk-ant-`). It is shown only once.
5. In the Appmixer Designer, connect an Anthropic Claude account and paste the key into the *API Key* field. Appmixer validates the key by listing the available models.

The API is billed per usage: the organization needs credits or a billing plan in *Settings* > *Billing*, otherwise the API calls fail.

## Backoffice configuration

No Backoffice configuration is required. The connector reads four optional keys that tune its behavior.

Configuration ID: `appmixer:ai:claude`. See [Connector Configuration](https://docs.appmixer.com/getting-started/services) for how to set it.

* `listModelsCacheTTL` – optional. How long, in milliseconds, the list of models (used by the model selector of the components) stays cached. Default: `3600000` (1 hour).
* `AI_AGENT_TOOL_MAX_ITEMS` – optional. When a component connected to the *tool* port of the *AI Agent* outputs several messages, the next component in the tool chain runs for at most this many of them; the rest are dropped and the truncation is logged. Default: `50`.
* `TOOLS_OUTPUT_POLL_TIMEOUT` – optional. How long, in milliseconds, the *AI Agent* waits for a tool chain to return its result through the *Tool Output* component. When it runs out, the agent gets an error for that tool call. Default: `120000` (2 minutes).
* `TOOLS_OUTPUT_POLL_INTERVAL` – optional. How often, in milliseconds, the *AI Agent* checks whether the tool chain has returned its result. Default: `300`.

```bash
appmixer service-config set appmixer:ai:claude -u -d '{
  "listModelsCacheTTL": 3600000,
  "AI_AGENT_TOOL_MAX_ITEMS": 50,
  "TOOLS_OUTPUT_POLL_TIMEOUT": 120000,
  "TOOLS_OUTPUT_POLL_INTERVAL": 300
}'
```


---

# 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.appmixer.com/connector-configuration/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.
