Can NoClick translate whole documents, not just short strings?

Yes. Alongside plain text translation, the node has a Translate Document operation for file-based content and Batch Translate Text for large jobs that cover many segments at once. If you do not know the source language, you can run Detect Language first, then translate into any supported target.

How do I connect the node to Google Translate?

The node authenticates with your Google Cloud credentials for the Cloud Translation API. Once connected, the same credential covers the text, document, and batch operations. You can start with the Basic operations for quick translations and move to the v3 operations when you need more.

Can a workflow react when a batch translation finishes?

Yes. The On Batch Operation Completed trigger fires when a batch job finishes, so a workflow can start the moment results are ready instead of polling for them. You can also call Get Operation Status to check on a running job at any point.

Can I keep specific terms translated a consistent way?

Yes. Create Glossary lets you define how particular terms should be translated, and List Glossaries shows the ones you already have. Reference a glossary in a batch translation so brand names, product names, and jargon come out the same every time.

What is the difference between the Basic and v3 operations?

Basic operations cover quick text translation, language detection, and listing languages. The v3 operations add document translation, batch jobs, glossaries, romanization, and operation status tracking. Choose Basic for simple one-off translations and v3 when you need scale or custom terminology.

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 Google Translate

Give an AI agent Google Translate as a tool and it can localize content itself instead of asking you to. It can translate text and documents, detect a language, romanize a script, kick off batch translation jobs, and build glossaries so product terms stay consistent, calling each operation as a tool while it works a task. Wire it into a coding agent in NoClick and translation becomes one more step it handles on its own.

Loading preview…

Opens a workflow with 12 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 Google Translate
A preset of real Google Translate operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Google Translate
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.

Google Translate

12 tools

Translate Text (v3)

Translate one or more strings with the v3 Advanced API.

Detect Language (v3)

Detect the source language of input text (v3 Advanced).

Get Supported Languages (v3)

List languages supported for translation/detection (v3 Advanced).

Romanize Text (v3)

Transliterate non-Latin-script text into Latin (romanization).

Translate Document (v3)

Translate a single document inline, preserving formatting (v3 Advanced).

Batch Translate Text (v3)

Async bulk text translation from/to Cloud Storage (returns an LRO).

Create Glossary (v3)

Create a glossary for custom terminology (returns an LRO).

List Glossaries (v3)

List glossaries in a project/location.

Get Operation Status (v3)

Poll the status of a long-running operation (batch/glossary jobs).

Translate Text (Basic)

Translate text using the v2 Basic API (API key).

Detect Language (Basic)

Detect the source language of text using the v2 Basic API (API key).

List Languages (Basic)

List supported languages using the v2 Basic API (API key).

Starting points

What you can build

When a support ticket comes in, detect its language and translate the message into English before it reaches your team.

Translate every new blog post or help doc into your target markets automatically as soon as it publishes.

When a batch translation job completes, pick up the results and push them back into your CMS or storage.

Romanize names and addresses written in non-Latin scripts so they sort and display correctly in your database.

Create a glossary of product and brand terms, then run batch translations that keep those terms consistent across every language.

Translate an uploaded document into a customer's preferred language and email the result back automatically.

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