Can a workflow react when a Phantom finishes running?

Yes. The On Phantom Finished trigger starts a workflow the moment a Phantom completes, and you can immediately call Get Container Result or Get Agent Output to pull the data it collected. That turns a finished scrape into an automatic hand-off instead of a manual download.

How do I connect Phantombuster to NoClick?

The node authenticates with your Phantombuster API key, which you copy from your account's org settings. Paste it into the credential form once and every Phantombuster operation in your workflows uses it.

Can it retrieve the leads a Phantom scraped?

Yes. Use Get Container Result and Get Container Output to fetch the data from a specific run, or Get Agent Output to read an agent's latest results. From there you can route the leads anywhere else on the canvas.

Can NoClick track how much my Phantoms are using?

The node exposes Export Agent Usage and Export Container Usage, so a workflow can pull usage figures for a Phantom or an individual run. Schedule it and you get a recurring record of consumption without checking the dashboard.

Does it support Phantombuster's AI features?

Yes. The AI Advice, AI Completion, and AI Task operations call Phantombuster's AI endpoints directly, so you can generate text or get recommendations inside the same workflow that pulled the scraped data.

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 PhantomBuster

Give an AI agent your Phantombuster account as a tool and it can act on scraped data the moment a Phantom is done, not just talk about it. It reads container results and agent output, checks on jobs by attaching to a container, exports usage, prunes stale lead lists, and calls Phantombuster's AI advice and completion operations, each as a tool it invokes while it works a task. Wire it into a hosted coding agent in NoClick and it can watch a scrape finish, grab the leads, and move them along without a human in the loop.

Loading preview…

Opens a workflow with 62 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 PhantomBuster
A preset of real PhantomBuster operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect PhantomBuster
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.

PhantomBuster

62 tools

Get Account

Fetch the current account info, plan/quota, and running agents.

Update Account

Update the current user's profile fields.

List Agents

List every agent (Phantom) in the workspace.

Get Agent

Fetch a single agent's details and configuration.

Get Agent Output

Fetch the incremental console output of an agent's most-recent run.

List Deleted Agents

List soft-deleted agents in the workspace.

Launch Agent

Start an agent run; returns a container ID.

Launch Agent (Queued)

Queue the agent to launch as soon as a slot is free.

Launch Agent (Sync)

Launch and block until completion, returning the result inline.

Stop Agent

Abort a running agent / its container.

Save Agent

Create or update an agent's configuration/arguments.

Delete Agent

Permanently remove an agent.

Unschedule All Agents

Remove all schedules from the org's agents.

List Containers

List execution containers (run history) for an agent.

Get Container

Fetch a single container's status/metadata for one run.

Get Container Output

Retrieve console output / progress / result-object URL for a run.

Get Container Result

Retrieve the structured result object (the scraped data) for a run.

Attach To Container

Attach to a running container and return its live output stream.

List Scripts

List all scripts (Phantom definitions) in the workspace.

Get Script

Fetch metadata for a single script.

Get Script Code

Retrieve the raw code of a script.

Save Script

Create or update a script's code/metadata.

Delete Script

Remove a script.

Set Script Visibility

Set a script's visibility.

Set Script Access List

Set a script's access list.

List Branches

List script branches.

Diff Branch

Diff a branch against production.

Create Branch

Create a script branch.

Delete Branch

Delete a script branch.

Release Branch

Release (deploy) a branch to production.

Get Organization

Fetch organization/workspace details.

Get Org Resources

Fetch resource/quota allocation for the org.

List Running Containers

List all currently-running containers across the organization.

List Agent Groups

List the org's agent groups (folders).

Save Agent Groups

Create/update the org's agent groups.

Export Agent Usage

Export per-agent usage as a report.

Export Container Usage

Export per-container usage as a report.

Get CRM Access

Fetch the org's CRM integration access.

Get CRM Resources

Fetch the org's CRM resources.

Save CRM Contact

Upsert a CRM contact.

Save Leads

Store / upsert lead records into workspace storage.

Save Many Leads

Upsert multiple leads (1-20) into workspace storage in one call.

Delete Leads

Delete multiple leads by identifier.

Get Leads By List

Fetch the leads contained in a lead list.

List Lead Lists

List all saved lead lists in the workspace.

Get Lead List

Fetch a single lead list by id.

Save Lead List

Create or update a lead list.

Delete Lead List

Delete a lead list.

Save Identity

Save an identity (session cookies for logged-in scraping).

Save Identity With Token

Save an identity using a connection token.

Generate Identity Token

Generate a token + magic link for the user to connect an identity.

Search Identities

Search stored identities.

Save Identity Event

Record an identity event.

List ICPs

List Ideal Customer Profiles (ICPs).

List Buyer Personas

List buyer personas.

AI Completion

Generate an AI text completion (PhantomBuster-hosted AI).

AI Advice

Get AI advice (PhantomBuster-hosted AI).

AI Task

Run an AI task (PhantomBuster-hosted AI).

Solve hCaptcha

Submit an hCaptcha challenge for solving.

Solve reCAPTCHA

Submit a reCAPTCHA challenge for solving.

SERP Search

Run a SERP (search-engine results) scrape via BrightData.

IP Geolocation

Resolve geographic location from an IP address.

Starting points

What you can build

When a Phantom finishes, pull its container result and pass the fresh leads straight into your CRM or a downstream enrichment step.

On every completed run, get the container output and post a short summary to Slack so the team sees new leads without opening Phantombuster.

Export container usage and agent usage on a schedule to keep a running tab on how many launches each Phantom is burning.

After a scrape completes, fetch the agent output, run it through an AI step, and delete stale entries from the old lead list to keep the data clean.

Generate an identity token and get CRM access at the start of a workflow so downstream steps act on the right account automatically.

Feed a finished Phantom's scraped profiles into the AI Task and AI Completion operations to draft outreach copy in the same run.

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