Can NoClick scrape a whole website, not just one page?

Yes. Crawl Website walks a site and returns every page as clean content, and you can watch progress with Get Crawl Status or stop early with Cancel Crawl. For a fixed set of URLs, Batch Scrape handles many pages at once, with Get Batch Scrape Status and Get Batch Scrape Errors to track the run.

Can it pull structured data instead of raw text?

Yes. Extract Structured Data returns JSON shaped to the fields you ask for, so a page becomes usable records rather than a wall of markdown. For sites that need navigation to reach the data, the autonomous Agent operation figures out the steps and extracts on its own.

Can a workflow react when a page changes?

Yes. Create a Monitor on any URL and the On Monitor Event trigger fires when Firecrawl detects a real content change, so you can alert a channel or run a follow-up job. There are also triggers for crawl, batch scrape, and Agent events, plus On Any Firecrawl Event to catch them all in one place.

How do I connect Firecrawl to NoClick?

The node authenticates with your Firecrawl API key, which you paste once when you add credentials. After that, every operation from Crawl Website to Extract Structured Data runs against your own account, and you can track spend with Get Credit Usage and Get Historical Credit Usage.

Can it handle pages that need clicks or a login?

Yes. Create an Interact Session and use Execute in Interact Session to click, fill forms, and navigate a live page before extracting, then Delete Interact Session to close it. This reaches content behind JavaScript, pagination, or a sign-in step that a plain scrape cannot.

What does it mean to connect an app to Claude Code?

You wire an integration node into the agent's tools handle. Each operation that app exposes becomes a tool Claude Code can call directly, so it can take real actions in that app instead of only describing them.

Do I need to write any code to set this up?

No. You pick the integrations, click to open the agent in NoClick, connect your accounts, and the tools are ready. There is no glue code to maintain.

Does Claude Code run on my own machine?

No. NoClick runs the harness for you in a hosted sandbox, so there is nothing to install and the agent can run on a schedule or from a trigger.

Can Claude Code use more than one app in a single run?

Yes. Wire as many integrations into the same agent as you need and it can use all of them together while completing a task.

Claude Code

Connect Claude Code to Firecrawl

Give an AI agent Firecrawl as a tool and it can go read the web itself instead of guessing at what a page says. It can scrape and crawl sites, batch scrape a list of URLs, extract structured data against a schema, and even run an autonomous Agent or click through a live page with an Interact Session, calling each operation as a tool while it works a task. Wire it into a hosted coding agent in NoClick and research or data-collection jobs that used to need a person become something the agent finishes end to end.

Loading preview…

Opens a workflow with 48 tools ready to use.

What happens next

Set up in minutes

The open button drops you into a guided setup. It asks exactly this, nothing else:

Choose where it runs
On your computer through your own Claude Code, or hosted in the cloud. The rest of setup adapts to your choice:
Pick what it can do in Firecrawl
A preset of real Firecrawl operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Firecrawl
One sign-in. The agent acts through your account, scoped to the operations you picked.
Add your personal MCP link
The last step mints a private MCP URL for this agent and walks you through exactly this, with your real link filled in. The page flips to Connected the moment your Claude Code first calls in.
Run this in your terminal
$claude mcp add --transport http noclick https://mcp.noclick.app/s/<your-link>
<your-link> is your personal server URL — setup mints it for you.

Exact capabilities

Tools Claude Code gets

Pick the operations you want and each becomes a tool the agent can call directly while it works.

Firecrawl

48 tools

Scrape URL

Scrape a single URL and return content as markdown / HTML / links.

Get Scrape Status

Poll an async scrape job by id.

Batch Scrape

Submit many URLs to scrape asynchronously; returns a job id.

Get Batch Scrape Status

Poll a batch scrape job by id.

Cancel Batch Scrape

Cancel an in-progress batch scrape job.

Get Batch Scrape Errors

Retrieve per-URL errors for a batch scrape job.

Crawl Website

Start an async crawl of a site from a starting URL; returns a job id.

Get Crawl Status

Poll a crawl job's status by id.

Cancel Crawl

Cancel an in-progress crawl job.

Get Crawl Errors

Retrieve per-URL errors and robots.txt-blocked URLs for a crawl job.

List Active Crawls

List all currently running crawl jobs for the account.

Crawl Params Preview

Generate suggested crawl parameters from a natural-language prompt + URL.

Map Website

Quickly return a complete list of URLs discovered on a website.

Search the Web

Web search returning results, optionally with full-page content scraped.

Search GitHub History

Search GitHub history.

Search Papers

Search academic papers.

Get Paper

Inspect or read a paper.

Find Related Papers

Find related papers.

Extract Structured Data

LLM-powered structured extraction from URLs (async; returns a job id). Deprecated by Firecrawl in favor of the agent operation.

Get Extract Status

Poll an extract job by id. Deprecated.

Agent (Autonomous Extract)

Autonomous AI web data gathering from a prompt + schema (async).

Get Agent Status

Poll an agent job by id.

Cancel Agent

Cancel an in-progress agent job.

Parse a File

Parse a remote file (PDF, DOCX, etc.) into markdown or other formats.

Create Interact Session

Create a Firecrawl interact session.

List Interact Sessions

List active Firecrawl interact sessions.

Execute in Interact Session

Execute code in a Firecrawl interact session.

Delete Interact Session

Delete a Firecrawl interact session.

Interact With Scrape Job

Execute code in the scrape-bound interact session.

Stop Scrape Interaction

Stop the scrape-bound interact session.

Get Credit Usage

Return remaining credits for the account.

Get Token Usage

Return LLM token usage (for extract/agent operations).

Get Historical Credit Usage

Return historical credit usage for the account's team.

Get Historical Token Usage

Return historical token usage for the account's team.

Get Queue Status

Inspect the account's current job queue depth/status.

List Team Activity

List recent API activity for the authenticated team.

Submit Endpoint Feedback

Submit feedback for a v2 job.

Submit Search Feedback

Submit feedback for a search job.

Ask Firecrawl Support

Ask the Firecrawl support agent.

Search Firecrawl Docs

Search Firecrawl docs with citations.

Create Monitor

Create a monitor.

List Monitors

List monitors.

Get Monitor

Get a monitor.

Update Monitor

Update a monitor.

Delete Monitor

Delete a monitor.

List Monitor Checks

List checks for a monitor.

Get Monitor Check

Get a single monitor check and page details.

Run Monitor

Run a monitor immediately.

Starting points

What you can build

When a crawl finishes, use the On Crawl Event trigger to load every scraped page into your database or a vector store automatically.

Feed a list of competitor URLs to Batch Scrape on a schedule, then compare the results to catch pricing and copy changes.

Point Extract Structured Data at a directory or listing page to pull names, prices, and links into clean JSON for your CRM.

Create a Monitor on a changelog or status page so the On Monitor Event trigger posts to Slack the moment the page actually changes.

Turn a research request into a Crawl Website run, wait for Get Crawl Status to report done, then summarize the whole site with an AI step.

Run an autonomous Agent to extract data from a site that needs navigation, and react to On Agent Event when it reports its results back.

Meet the runner

About Claude Code

Claude Code is Anthropic's command-line coding agent. In NoClick you run it as a hosted agent and connect your real apps to its tools handle, so it does far more than write code. Wire in an integration and Claude Code can read and act on Slack, Linear, your database, and more on its own, calling each one as a tool while it works. It is the same capable agent, pointed at your actual workflows instead of a sandbox.

Careful multi-step planning before it acts

Reliable on long, structured tasks

Reads context thoroughly before making changes

Comfortable across code, data, and APIs

Good to know