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

# Agent quickstart

> Paste one prompt into Claude Code, Cursor or another coding agent, and it sets Prefetch up for you: key, MCP connection or app code, and a first verified call.

Copy this prompt into your coding agent. It asks you for your API key, sets up Prefetch the way your project needs, and checks that a first call works.

```text Prompt for your coding agent theme={"theme":"css-variables"}
Set up the Prefetch API (https://prefetch.io) in this project.

Docs index: https://docs.prefetch.io/llms.txt (full text: https://docs.prefetch.io/llms-full.txt).
Read only the pages you need.

1. Ask me for my Prefetch API key. I get it from https://prefetch.io/dashboard.
   Never print it, log it, or commit it.
2. Store it as PREFETCH_API_KEY: in .env for application code (make sure .env is in .gitignore),
   or in this agent's MCP config if I only want to use Prefetch from chat.
3. Ask me which I want, then do it:
   a. MCP for this agent: add the remote MCP server https://api.prefetch.io/mcp
      (Claude Code: `claude mcp add --transport http prefetch https://api.prefetch.io/mcp`,
      then authenticate from /mcp; Cursor: add it to .cursor/mcp.json).
   b. Application code: call the REST API with the X-API-Key header. There is no SDK; use the
      project's existing HTTP client. Every response is {success, data, meta}; on failure branch
      on error_code and retry only when retryable is true.
4. Verify: call GET https://api.prefetch.io/classify?url=https://stripe.com (5 credits) and
   show me data.classification.category.
5. Tell me what you changed, and link the docs pages for the endpoints I'm likely to use.
```

## What the agent will do

**1. Ask for your key**

Agents can't sign up for you. Create a key on the [dashboard](https://prefetch.io/dashboard) and paste it when asked.

**2. Pick a setup**

**MCP** gives the agent Prefetch tools in chat: scrape, enrich, crawl, monitor and more. **App code** adds REST calls to your project. See [MCP server](https://docs.prefetch.io/mcp/overview.md) and the [API reference](https://docs.prefetch.io/api-reference/introduction.md).

**3. Verify**

One `/classify` call proves the key and the connection work. It costs 5 credits.

## Docs for agents

* [`llms.txt`](https://docs.prefetch.io/llms.txt): an index of every page.
* [`llms-full.txt`](https://docs.prefetch.io/llms-full.txt): every page in one file.
* Every page has a menu to copy it as markdown, or open it in Claude, ChatGPT or Cursor.

## Next

> [card] [MCP server](https://docs.prefetch.io/mcp/overview.md)
>
> Connect Claude, ChatGPT, Cursor or any MCP client.

> [card] [Recipes](https://docs.prefetch.io/recipes/overview.md)
>
> Each recipe has a prompt you can hand to your agent.


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