Crawl4AI MCP server for AI agents and assistants

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Crawl4AI MCP or direct API to search the web, crawl pages, extract structured data, and monitor websites through natural language.

Crawl4AI logoCrawl4AI
Api Key

Crawl4AI is a web scraping and search service for extracting structured data from websites. It helps teams collect clean web data, monitor pages, and verify leads at scale.

51 Tools

Try Crawl4AI now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
Crawl4AI
Try asking
TOOLS

Supported Tools

Every Crawl4AI action and event your agent gets out of the box.

Answer Question

Answer a question from web sources and return the answer with citations when available.

Cancel Recipe Job

Stop a running recipe job.

Cancel Site Crawl

Stop a running site crawl job; the job ends in the paused state.

Read Monitor Changes

Read the oldest new changes across monitors and mark the returned feed items as read.

Create Monitor

Create a page-change monitor, or return the existing equivalent monitor, that performs recurring credit-consuming checks until paused or deleted and can send configured notifications.

Create Plan Checkout

Create an account-specific Stripe checkout flow for a Crawl4AI paid plan.

Delete Monitor

Permanently delete one page-change monitor and its history.

Estimate Cost

Estimate the minimum and maximum Crawl4AI credits for a proposed API request without running that request.

Extract Prices

Read pricing pages for up to 20 site-and-country combinations and return documented plans, billing periods, add-ons, discounts, trials, and source quotes.

Extract Structured Data

Extract structured records from exactly one URL or supplied content using an instruction, a JSON Schema, or both.

Forget Email Verification

Request permanent removal of Crawl4AI's stored verification answer for one email.

Get Billing Balance

Return the connected account's current free-credit balance, allowance, plan, tier, card status, spending, and top-up balance.

Get Lead Company

Get one private-preview Lead company by domain, LinkedIn page, or an unambiguous name optionally narrowed by country.

Get Email Verification Job

Get later results for a batch email verification job, including background retries.

Get Monitor

Return one page-change monitor's configuration, health, baseline, cost, and notification settings.

Get Monitor Version

Download the page exactly as Crawl4AI captured it for monitor evidence, returned as a Markdown text file.

Get Lead Person

Get one private-preview Lead person and held contact data by one documented lookup.

Get Lead Person Email

Get private-preview personal contact data: one person's checked email by one documented lookup.

Get Lead Person Phone

Get private-preview personal contact data: a person's direct and company phones by one documented lookup.

Get Price History

Return up to 1,000 observed price changes for one domain and optional country, newest first.

Get Prices and Plans

Return Crawl4AI's current credit prices, effort levels, plans, allowances, and request limits from the authoritative live catalog.

Get Recipe Health

Get the latest regional health check and release stage for every recipe, keyed by its live catalog name.

Get Recipe Job

Get a recipe job's status, progress counts, pause reason, and usage.

Get Recipe Job Results

Download a recipe job's result rows as an NDJSON file.

Get Scrape Job

Return a scrape job's current status, URL counts, and credit usage, with optional per-URL detail.

Get Scrape Job Results

Download one page of up to 500 scrape job results as NDJSON; pass the next result offset explicitly to retrieve another page.

Get SERP

Return structured Google rankings through Crawl4AI's GET transport, including source selection and the fixed device, engine, and result-type controls.

Get Site Crawl Job

Read a site crawl job's state, progress counts, completion deadline, usage, and pause reason when applicable.

Get Site Crawl Results

Download one page of up to 500 site crawl result rows as NDJSON, optionally continuing after a previously returned sequence number.

List Billing Topups

List account payments and credit additions newest first, including receipt URLs, one cursor-controlled page at a time.

List Lead Industries

Return documented LinkedIn industry names or names closest to query words.

List Monitor Events

List one monitor's change and health timeline oldest first, including facts and links to captured evidence versions.

List Monitors

List the connected account's page-change monitors, optionally filtered by agent label.

List Recipes

List the live ready-made scraper catalog, including each recipe's dynamic input schema, output fields, cost, stage, and health.

Purchase Extra Credits

Immediately charge the saved card for the connected account's paid Crawl4AI plan and add non-expiring extra credits.

Retry Scrape Job

Re-run only the failed URLs in an existing scrape job.

Run Recipe

Run one synchronous catalog recipe with inputs that match its current schema.

Scan Site URLs

Discover a site's known public page URLs from sitemaps, its home page, Common Crawl, and optionally the Wayback Machine without crawling each URL.

Scrape Page

Fetch one public web page and return its Markdown, HTML, and optional parsed links, media, metadata, or tables.

Scrape Pages

Scrape up to 50 public URLs with shared options and return a downloadable NDJSON file of completion rows followed by a final summary row.

Search Lead Companies

Search private-preview Lead companies by documented company filters and optional description-ranking words, one provider-cursor page at a time.

Search Lead People

Search private-preview Lead people by documented company and person filters.

Search SERP

Return structured Google result ranks and SERP blocks for a localized query and explicit result page.

Search Web

Search the web for ranked, cleaned results, optionally including related questions, queries, news, videos, and discussions.

Submit Recipe Job

Submit an asynchronous run for a job-capable recipe using its dynamic live catalog inputs.

Submit Scrape Job

Submit up to 10,000 public URLs for asynchronous scraping and return a job identifier for status polling and paged result retrieval.

Submit Site Crawl

Start a background crawl of public pages within one site and return the job identifier used to inspect its status and results.

Update Monitor

Change a monitor's watch rule, schedule, notifications, schema, name, or paused state.

Verify Email

Check whether one email can receive mail.

Verify Email Domain

Check one domain's mail acceptance, provider, gateway, catch-all, SPF, and DMARC results.

Verify Emails

Check one to 1,000 email addresses without sending mail.

SETUP GUIDE

Connect Crawl4AI MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
Install the Composio SDK and your agent framework
2

Create a session with MCP enabled

typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["crawl4ai"],
  mcp: true,
});
Create a session scoped to Crawl4AI and read its MCP URL and headers
3

Connect your agent to the MCP server

typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "Search the web for the latest pricing pages from three competing project management tools and summarize their plans.",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
Pass the session's MCP URL and headers to your agent and run a Crawl4AI request
SETUP GUIDE

Connect Crawl4AI API Tool with your Agent

1

Install Composio

typescript
npm install @composio/core @composio/openai openai
Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
2

Create a Composio session

typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["crawl4ai"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to Crawl4AI
3

Run Crawl4AI tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Search the web for the latest pricing pages from three competing project management tools and summarize their plans." }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
Send a request, execute the Crawl4AI tool calls through the session, and print the final answer

Why Use Composio?

AI Native Crawl4AI Integration

  • Supports both Crawl4AI MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable web scraping and extraction
  • Rich coverage for search, crawling, monitoring, lead intelligence, and email verification

Managed Auth

  • Securely stores and uses your Crawl4AI API key without exposing it to agents
  • Central place to manage, scope, and revoke Crawl4AI access
  • Per user and per environment credentials instead of hard-coded keys

Agent Optimized Design

  • Tools are tuned using real error and success rates to improve reliability over time
  • Structured outputs help agents work with extracted page content and search results
  • Comprehensive execution logs show what ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Crawl4AI
  • Scoped, least privilege access to Crawl4AI resources
  • Full audit trail of agent actions to support review and compliance

Rolling this out across your team?

Give your team centralized access control across every framework with Composio’s MCP Gateway.

EXPLORE MCP GATEWAY
FAQ

Frequently asked questions

Start with Crawl4AI.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Crawl4AI tool your agent needs.Free to start.

Start building