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

# API & MCP

Run Frase research, audits, and publishing from an AI assistant or your own code instead of clicking through the app.

## Connect Frase to your AI assistant with MCP

MCP lets assistants like Claude, ChatGPT, and Cursor use Frase for you. Ask in plain language, like *"Find a keyword opportunity, write a brief, and publish the article as a draft,"* and the assistant runs the steps in Frase.

{% stepper %}
{% step %}

### Open Frase MCP in Claude

Go to [Frase MCP in the Claude Directory](https://claude.ai/customize/connectors/directory/frase) and click **Connect**.
{% endstep %}

{% step %}

### Sign in to Frase

No API key needed.
{% endstep %}
{% endstepper %}

**Using ChatGPT?** In Frase, go to **Settings → API Keys** and click **Connect in ChatGPT** to add the [official Frase app in ChatGPT](https://chatgpt.com/plugins/plugin_asdk_app_6a8768ef78508191958cc33d37b7f6c8). For Cursor or a manual install, use the [npm package](https://www.npmjs.com/package/@frase/mcp-server) and add **next.frase.io/api/mcp** as a connector.

{% hint style="success" %}
Once MCP is connected, [this article ](/automations/automate-with-frase-mcp.md)walks you through how to use it and best practices.
{% endhint %}

## Build with the Frase API

The Frase API is a REST API with 50+ endpoints for content and briefs, SERP analysis, AI visibility, site audits, topic research, analytics, and publishing. Responses come back as JSON.

See the [Frase API documentation](https://next.frase.io/api/docs#description/introduction) for more technical details.

{% hint style="info" %}
Check your remaining API runs in **Settings → Billing & Usage**. Each task you run through the API still uses the same plan credits it would in the app.
{% endhint %}


---

# 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.frase.io/integrations/api-and-mcp.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.