Skip to main content
Connect your AI assistant, coding agent or application to Zenrows once, and it can read any page, extract structured data, crawl a site, run large jobs and drive a real browser on your behalf. Every recipe in this Academy includes an Ask your AI agent prompt you can paste as soon as you’re connected. Uses: Zenrows MCP server, Zenrows CLI, Zenrows docs for agents

Choose your path

You don’t need an account to start. The local MCP server (npx -y @zenrows/mcp) creates a Free account with 5,000 credits for its first billing period on its first tool call, and the CLI the first time it runs without a key, and you can claim it later, keeping its key and usage. An unclaimed account is not renewed after that first period. See Agent signup and unclaimed accounts. The remote server and the Claude connector sign you in with OAuth, where you can log in or create a Free account. To use an account you already have, copy your key from the dashboard.

Connect Claude

Claude connects to the hosted Zenrows MCP server and signs you in with OAuth, so there is no key to copy. Follow Claude for the web, desktop and mobile apps. In Claude Code, install the Zenrows plugin. It adds the MCP server and the Zenrows skills that teach Claude which Zenrows tool fits each task:
Claude Code
Then run /mcp, select zenrows and sign in. To skip sign-in, add the local server instead. With no key, it creates a Free account for you:
Terminal
To use a key you already have:
Terminal

Connect any MCP client

The remote server takes the same two settings in every MCP client: the server URL and your key as a Bearer token, or OAuth sign-in where the client supports it. Clients that run servers locally use the @zenrows/mcp package instead. Leave the env block out to start without a key, or keep it to use yours:
JSON
Step-by-step guides with each client’s config file path: Cursor, VS Code, Windsurf, Zed, JetBrains, OpenCode, Claude Desktop. Both servers expose the same tools: scrape and extract for single pages, crawl_* for whole sites, batch_* for URL lists, and the browser_* tools for the Zenrows Browser. The local server also has account_signup_answer, which it needs only when it creates its own account. See the tool reference.

Set up your coding agent with the CLI

The Zenrows CLI prepares a project for your coding agents in one command: it signs you in, prints the MCP config for each agent, and installs Zenrows skills, the playbooks that tell an agent which primitive and parameters fit a task.
Terminal
To add one client later, zenrows plugin install <client> installs the MCP config and every skill together. Supported clients: claude-code, cursor, vscode, windsurf, gemini, codex, opencode, generic. See Skills and MCP setup from the CLI.

Connect your own agent

Agents built on an LLM API take the remote server as a tool definition. With the OpenAI Responses API:
Python
Framework guides: Anthropic API, Claude Agent SDK, OpenAI Agents SDK, Google ADK, LangChain, LlamaIndex, Mastra, CrewAI. To build the agent loop yourself, follow Build a research agent with live web data.
An agent with no Zenrows account has two options. The free one: run the local MCP server or the CLI with no key, and it creates a Free account to claim later. Or pay per request with no account at all: the agent buys and calls Fetch and Extract on its own. See Agentic payments.

Give your agent the Zenrows docs

When a coding agent writes Zenrows code, give it the docs as context so it uses exact parameter names:
  • Docs MCP server: add https://docs.zenrows.com/mcp to your client. It gives the agent a search_zenrows tool over these docs.
  • llms.txt: docs.zenrows.com/llms.txt indexes every page, and llms-full.txt holds the full text.
  • Any page as markdown: add .md to a page URL, or use the Copy page menu at the top of every page to send it to Claude, ChatGPT or Perplexity.
  • OpenAPI: Fetch, Extract and Batch are described in OpenAPI 3.1 at https://www.zenrows.com/openapi.json.

Check the connection

Paste this prompt into your assistant:
Your agent calls account_usage and scrape, and answers with your plan usage and the product count. You can also confirm the server from a terminal: a tools/list call returns every Zenrows tool.
cURL

Example output

An illustrative reply to the prompt above. Your agent’s wording and your usage figures differ:

Troubleshooting

  • The assistant answers from memory instead of the page: name the tool in the prompt, for example “Use Zenrows to read…”.
  • 401 from the server: the Bearer token isn’t a valid Zenrows API key. Copy the key again from the dashboard, with the Bearer prefix.
  • Signup refused, too many new accounts from this network: each network can create 3 accounts in 24 hours. Set ZENROWS_API_KEY to a key you already have. In CI, store the key as a secret; see In CI.
  • The local server doesn’t start: npx needs Node.js 20.6 or later on your PATH.

Prompts that put Zenrows MCP to work

A prompt library for every primitive and workflow.

Let your AI assistant browse with Browser tools

Drive the Zenrows Browser with plain-language instructions.

Build a research agent with live web data

Wire Zenrows into your own agent loop.

Automate scraping from your terminal with the CLI

Script fetch, extract, crawl and batch with the CLI.