Does the agent send email on its own?

For new mail it uses Create Email Draft, so the message waits in your drafts until you send it. It can forward an existing thread if you expose Forward Email Message, so leave that operation off if you want every send to stay manual.

Can it permanently delete the wrong thread?

It only has the operations you allowlist, and Permanently Delete Message and Permanently Delete Thread are separate ones you can withhold. Expose the draft and label operations and leave the delete ones out if you want it to tidy up without hard-deleting.

How do the two accounts stay secure?

You connect a Gmail credential and a BigQuery credential once, and both resolve server-side at run time. The model never sees the tokens, and each credential's scopes limit what the agent can do in that account.

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 BigQuery and Gmail

Give Claude Code your BigQuery and Gmail together and it can make a warehouse change and prepare the message about it in one pass. It creates and drops datasets, tables, routines, and models in BigQuery, then drafts, labels, forwards, and cleans up mail in Gmail. BigQuery is where the data work happens, and Gmail is how the people who care about it hear the news. Because new mail lands as a draft you approve, the announcement never goes out until you say so.

Loading preview…

Opens a workflow with 66 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 BigQuery
A preset of real Google BigQuery operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Pick what it can do in Gmail
A preset of real Gmail operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Google BigQuery
One sign-in. The agent acts through your account, scoped to the operations you picked.
Connect Gmail
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 BigQuery

38 tools

Run Query

Run a SQL query and return results inline (synchronous, bounded by timeout).

Get Query Results

Page through the results of a (possibly async) query job.

Insert Job

Start a query / load / extract / copy job (async).

Get Job

Fetch a job's status and statistics (poll until DONE).

List Jobs

List jobs in a project (filter by state, time range).

Cancel Job

Request cancellation of a running job.

Delete Job

Delete a job's metadata.

List Datasets

List datasets in the project.

Get Dataset

Fetch dataset metadata.

Create Dataset

Create a new dataset.

Update Dataset

Full replace of dataset metadata (PUT).

Patch Dataset

Partial update of dataset metadata (PATCH).

Delete Dataset

Delete a dataset.

List Tables

List tables/views in a dataset.

Get Table

Fetch table metadata/schema.

Create Table

Create a table or view with a schema.

Patch Table

Partial update of a table (add columns, set expiration, etc.).

Update Table

Full replace of table metadata (PUT).

Delete Table

Delete a table or view.

Stream Insert Rows

Streaming insert of JSON rows into a table (real-time append).

List Table Data

Read rows from a table directly (paginated, no SQL).

List Routines

List stored procedures / UDFs / TVFs in a dataset.

Get Routine

Fetch a routine definition.

Create Routine

Create a stored procedure / UDF / TVF.

List Models

List BigQuery ML models in a dataset.

Get Model

Fetch BQML model metadata.

Delete Model

Delete a BQML model.

Get Service Account

Return the BigQuery service account for the project (KMS/transfer grants).

List Projects

List projects the caller can access (for project picker UIs).

Undelete Dataset

Restore a dataset within its time-travel window (datasets.undelete).

Update Routine

Replace a routine's full definition (routines.update, PUT).

Delete Routine

Delete a routine (routines.delete).

Patch Model

Update mutable BQML model metadata (models.patch).

Get Table IAM Policy

Get the IAM policy for a table (tables.getIamPolicy).

Set Table IAM Policy

Set the IAM policy for a table (tables.setIamPolicy).

Test Table IAM Permissions

Test the caller's permissions on a table (tables.testIamPermissions).

List Row Access Policies

List row access policies on a table (rowAccessPolicies.list).

Get Row Access Policy

Get a single row access policy (rowAccessPolicies.get).

Gmail

28 tools

Send Email Message

Configuration for sending an email

Fetch Emails from Inbox

Configuration for reading emails from inbox

Fetch Email Message

Configuration for getting a specific message

Fetch Email Attachment

Configuration for fetching a message attachment

Permanently Delete Message

Configuration for permanently deleting a message

Move Message to Trash

Configuration for moving a message to trash

Restore Message from Trash

Configuration for removing a message from trash

Update Message Labels

Configuration for modifying message labels

Reply to Email Message

Configuration for replying to an email

Forward Email Message

Configuration for forwarding an email

Create Email Draft

Configuration for creating a draft

List Email Drafts

Configuration for listing drafts

Fetch Email Draft

Configuration for getting a specific draft

Update Email Draft

Configuration for updating a draft

Delete Email Draft

Configuration for deleting a draft

Send Email Draft

Configuration for sending a draft

List Email Labels

Configuration for listing all labels

Create Email Label

Configuration for creating a label

Fetch Email Label

Configuration for getting a label

Update Email Label

Configuration for updating a label

Delete Email Label

Configuration for deleting a label

List Email Threads

Configuration for listing threads

Fetch Email Thread

Configuration for getting a specific thread

Move Thread to Trash

Configuration for moving a thread to trash

Restore Thread from Trash

Configuration for restoring a thread from trash

Update Thread Labels

Configuration for modifying thread labels

Permanently Delete Thread

Configuration for permanently deleting a thread

Fetch User Profile

Configuration for getting user profile

Starting points

What you can build

After creating a new BigQuery dataset and its tables for a project, draft a Gmail announcement and label it for the data team.

When you cancel a BigQuery job, draft a Gmail note to the pipeline owner explaining why and forward them the original alert thread.

During cleanup, delete deprecated BigQuery tables and permanently delete the stale Gmail alert threads tied to them.

Forward the escalation thread about a failed load to your data lead and create the BigQuery table the job was supposed to build.

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