# Bright Data for AI agents. One API key, ready-made tools.

> Get search engine results, fetch hard-to-reach pages and collect structured web data with Bright Data for your agent with one Agent200 API key.

- Page: https://www.agent200.com/connectors/bright-data/
- Category: Search and data
- Authentication: Agent200 API key
- Identifier in code: `bright_data`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-18

## Instructions for AI agents

Connector: Bright Data, through Agent200. In code: "bright_data".
What it does: Get search engine results, fetch hard-to-reach pages and collect structured web data with Bright Data for your agent with one Agent200 API key.
Page: https://www.agent200.com/connectors/bright-data/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Agent200 reaches Bright Data with the project's Agent200 API key. No separate Bright Data key is needed.
3. Read tools: bright_data_search_engine, bright_data_scrape_url, bright_data_get_snapshot_status, bright_data_get_snapshot. Write tools: bright_data_trigger_scraper. Name "bright_data" in the tools of a request; the model decides which tool to call.
4. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
5. Before a write, confirm with the user, unless they asked for that exact change.
6. For setup with a specific framework, follow its guide:
   https://www.agent200.com/connectors/bright-data/framework/claude/
   https://www.agent200.com/connectors/bright-data/framework/chatgpt/
   https://www.agent200.com/connectors/bright-data/framework/claude-code/
   https://www.agent200.com/connectors/bright-data/framework/muse/
   https://www.agent200.com/connectors/bright-data/framework/grok-bot/
   https://www.agent200.com/connectors/bright-data/framework/openai-dots/
   https://www.agent200.com/connectors/bright-data/framework/claude-duet/
   https://www.agent200.com/connectors/bright-data/framework/hermes-agent/
   https://www.agent200.com/connectors/bright-data/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the Bright Data connector, your agent collects web data with your project's Agent200 API key, with no separate Bright Data account or key needed. It can get search engine results, fetch a page's content, and start a scraper for a site and download the structured results, using only the tools your project allows.

Bright Data is a web data platform for proxies, scraping and ready-made datasets.

## Bright Data tools

- **Search the web** (`bright_data_search_engine`, read): Get search engine results for a query.
- **Fetch a page** (`bright_data_scrape_url`, read): Get the content of a web page as HTML or Markdown.
- **Start a scraper** (`bright_data_trigger_scraper`, write): Start a collection job on a site scraper for a list of URLs.
- **Check a job** (`bright_data_get_snapshot_status`, read): Get the progress of a collection job.
- **Download results** (`bright_data_get_snapshot`, read): Download the structured results of a finished job.

## Limits you can set

**Turn single tools on or off.** Let the agent search and fetch pages, and switch off `bright_data_trigger_scraper` so it can never start a collection job.

**Restrict what the agent reaches.** Choose the endpoints a project may use, for example search results but not site scrapers. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Run with the Bright Data tools

Name the model and the tools. The model decides which Bright Data tools to call, and Agent200 executes them with your Agent200 API key.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "Get the top Google results for best CRM for startups",
    tools: ["bright_data"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Example requests

- "Get the top Google results for best CRM for startups"
- "Fetch the text of this product page"
- "Collect the details of these Amazon product links"
- "Is my LinkedIn company data job done"

## Guides: Bright Data with your AI framework

- [Bright Data + Claude](https://www.agent200.com/connectors/bright-data/framework/claude.md): Connect Bright Data to Claude through Agent200's MCP server: no separate key, ready-made tools and one API key.
- [Bright Data + ChatGPT](https://www.agent200.com/connectors/bright-data/framework/chatgpt.md): Give ChatGPT access to Bright Data through Agent200: managed OAuth, ready-made tools and one API key.
- [Bright Data + Claude Code](https://www.agent200.com/connectors/bright-data/framework/claude-code.md): Have Claude Code build a Bright Data agent with the Agent200 SDK: no separate key, ready-made tools and one API key.
- [Bright Data + Muse](https://www.agent200.com/connectors/bright-data/framework/muse.md): Connect Bright Data to Muse through Agent200's MCP server: no separate key, ready-made tools and one API key.
- [Bright Data + Grok Bot](https://www.agent200.com/connectors/bright-data/framework/grok-bot.md): Connect Bright Data to Grok Bot through Agent200's MCP server: no separate key, ready-made tools and one API key.
- [Bright Data + OpenAI Dots](https://www.agent200.com/connectors/bright-data/framework/openai-dots.md): Give OpenAI Dots access to Bright Data through Agent200: managed OAuth, ready-made tools and one API key.
- [Bright Data + Claude Duet](https://www.agent200.com/connectors/bright-data/framework/claude-duet.md): Connect Bright Data to Claude Duet through Agent200's MCP server: no separate key, ready-made tools and one API key.
- [Bright Data + Hermes Agent](https://www.agent200.com/connectors/bright-data/framework/hermes-agent.md): Connect Bright Data to Hermes Agent through Agent200's MCP server: no separate key, ready-made tools and one API key.
- [Bright Data + OpenClaw](https://www.agent200.com/connectors/bright-data/framework/openclaw.md): Connect Bright Data to OpenClaw through Agent200's MCP server: no separate key, ready-made tools and one API key.

## FAQ

### Do I need my own Bright Data API key?

No. Your Agent200 API key reaches Bright Data, so there is no separate provider key to collect, store or rotate.

### Can I limit what my agent can do in Bright Data?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

## Related connectors

- [Tavily](https://www.agent200.com/connectors/tavily.md): Web search built for agents, reached with your Agent200 API key.
- [Exa](https://www.agent200.com/connectors/exa.md): Search the web by meaning, read page contents and find similar pages, reached with your Agent200 API key.
- [Firecrawl](https://www.agent200.com/connectors/firecrawl.md): Scrape pages into Markdown, crawl and map sites, and extract structured data, reached with your Agent200 API key.
- [Brave Search](https://www.agent200.com/connectors/brave-search.md): Search the web, news, images and videos from Brave's independent index, reached with your Agent200 API key.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
