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 Vast Ai

Run Claude Code as a hosted agent in NoClick with Vast Ai wired into its tools handle. It can use Vast Ai 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 22 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 Vast Ai
A preset of real Vast Ai operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Vast Ai
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.

Vast Ai

22 tools

Get Current User

Read the authenticated account's profile and balance.

List Instances

Read one page of your instances; pass data.next_token as after_token.

Get Instance

Read one instance by contract ID.

Create Instance

Accept an offer and create a paid instance.

Manage Instance

Start, stop or relabel an instance; state changes are asynchronous.

Destroy Instance

Destroy an instance and its local data permanently.

Reboot Instance

Request an instance reboot.

Recycle Instance

Request recycling of an instance container.

Change Bid

Change an interruptible instance's hourly bid price.

Request Logs

Request a log download URL without downloading the external file.

Search Offers

Search a bounded set of GPU offers with documented comparison filters.

List Volumes

List your rented persistent volumes.

Search Volumes

Search one bounded set of volume offers.

Rent Volume

Rent a paid persistent volume from a volume offer.

Delete Volume

Delete a rented volume and its stored data.

List Invoices

Read one page of billing transactions within a date range.

List Charges

Read one page of per-contract charges within a date range.

List Ssh Keys

List the public SSH keys belonging to your account.

Create Ssh Key

Add an account SSH key; Vast.ai also adds it to current instances.

Delete Ssh Key

Delete a public SSH key from your account.

Attach Ssh Key

Attach a public SSH key to one instance.

Detach Ssh Key

Detach a public SSH key from one instance by key ID.

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