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 Abyssale

Run Claude Code as a hosted agent in NoClick with Abyssale wired into its tools handle. It can use Abyssale directly while it works. No glue code, nothing to install. Click below to open a ready-to-run agent and connect your account.

Loading preview…

Opens a workflow with 20 tools ready to use.

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 Abyssale
A preset of real Abyssale operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Abyssale
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. Claude Code connects when a session starts — run claude, or restart a running one.
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.

Tools Claude Code gets

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

Abyssale

20 tools

List Designs

Search designs by name and project, returning one explicit page.

Get Design

Read a design, its formats and customizable layers.

Delete Design

Permanently delete a design. This cannot be undone.

Rename Design

Rename a design.

Move Design

Move a design into an existing workspace project.

Get Design Format

Read one format by stable UID or format name.

Create Dynamic Image Url

Create a dynamic image URL for a static design.

Generate Image

Generate one image synchronously, spending workspace generation credits.

Generate Media

Queue multi-format media; poll Get Generation Request for completion.

Get File

Read generated asset metadata and file URLs without downloading bytes.

Get Generation Request

Poll a generation request once. A 202 means generation is still running.

List Fonts

Search fonts by name, type and category.

Get Credits

Read remaining workspace generation and AI credits.

List Projects

Read workspace projects; also proves the connected account can read them.

Create Project

Create a workspace project with a unique name.

List Workspace Templates

Read the workspace's shared templates, optionally filtered by category.

List Workspace Template Categories

Read categories for the workspace template library.

Duplicate Workspace Template

Queue duplication of a workspace template into an existing project.

Get Duplication Request

Poll template duplication once; statuses expire after seven days.

Export Banners

Queue a ZIP export; callback_url receives the asynchronous result.

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