> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to Google Cloud Storage

The Google Cloud Storage connector lets your AI agent act in each user's Google Cloud Storage account. Each user signs in to Google Cloud Storage once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 22 tools.

**Authentication:** OAuth 2.0
**Categories:** Files & Documents, Developer Tools
**Tools:** 22: 10 read, 9 write, 3 destructive
**Users sign in with:** OAuth
**OAuth app:** Your own Google Cloud Storage app
**Built by:** Scalekit connector
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=GOOGLECLOUDSTORAGE)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Google Cloud Storage connection

   In **AgentKit > Connections**, create a Google Cloud Storage connection and copy its redirect URI. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### Register an OAuth app

   Google Cloud Storage connections use your own OAuth app. Register one with Google Cloud Storage and add the redirect URI you copied.

   Then enter the app's Client ID and Client Secret on the Google Cloud Storage connection.

5. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'googlecloudstorage'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Google Cloud Storage:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'googlecloudstorage_bucket_get',
     toolInput: { bucket: 'YOUR_BUCKET' },
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "googlecloudstorage"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Google Cloud Storage:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={"bucket":"YOUR_BUCKET"},
       tool_name="googlecloudstorage_bucket_get",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'googlecloudstorage_bucket_get',
  toolInput: {
    bucket: '<bucket>',
  },
  connector: 'googlecloudstorage',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="googlecloudstorage_bucket_get",
    tool_input={
        "bucket": "<bucket>",
    },
    connection_name="googlecloudstorage",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `googlecloudstorage_bucket_get`

Get Bucket · Read-only

Get the settings of one Cloud Storage bucket.
Returns its location, storageClass, versioning, lifecycle, iamConfiguration, labels and metageneration.
Use this when you know the bucket name. Use googlecloudstorage_buckets_list to find buckets.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `projection` (`string`, optional): Set to full to include ACLs in the response, or noAcl to leave them out. Example: noAcl. One of: `full`, `noAcl`.

Example input: `{"bucket":"<bucket>"}`

### `googlecloudstorage_bucket_iam_policy_get`

Get Bucket IAM Policy · Read-only

Get the IAM policy of a Cloud Storage bucket.
Returns the policy's bindings (role and members), etag and version.
Use this to see who has access to a bucket. Use googlecloudstorage_bucket_permissions_test to check the caller's own access.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `options_requested_policy_version` (`integer`, optional): Policy version to return. Use 3 to see conditional role bindings. Example: 3

Example input: `{"bucket":"<bucket>"}`

### `googlecloudstorage_bucket_permissions_test`

Test Bucket Permissions · Read-only

Check which of the given permissions the connected user has on a Cloud Storage bucket.
Returns the subset of the permissions that are granted.
Use this before a write to confirm access. Use googlecloudstorage_bucket_iam_policy_get to see the whole policy.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `permissions` (`array`, required): Permissions to check. Example: ["storage.objects.list", "storage.objects.create"]

Example input: `{"bucket":"<bucket>","permissions":["storage.objects.list","storage.objects.create"]}`

### `googlecloudstorage_buckets_list`

List Buckets · Read-only

List the Cloud Storage buckets in a Google Cloud project.
Returns each bucket's name, location, storageClass, timeCreated and labels, plus nextPageToken when there are more.
Use this to find a bucket. Use googlecloudstorage_bucket_get for one bucket's full settings.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project` (`string`, required): Google Cloud project ID or number. Example: my-project-123
- `max_results` (`integer`, optional): Maximum number of buckets per page. Example: 100
- `page_token` (`string`, optional): nextPageToken from the previous page. Example: CgdyZXBvcnRz
- `prefix` (`string`, optional): Only return buckets whose names start with this text. Example: acme-

Example input: `{"project":"<project>"}`

### `googlecloudstorage_folders_list`

List Folders · Read-only

List the folders of a Cloud Storage bucket that has hierarchical namespace enabled.
Returns each folder's name, createTime and metageneration, plus nextPageToken.
Use this only for hierarchical-namespace buckets. For other buckets, use googlecloudstorage_objects_list with delimiter /.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `page_size` (`integer`, optional): Maximum number of folders per page. Example: 100
- `page_token` (`string`, optional): nextPageToken from the previous page. Example: CgdyZXBvcnRz
- `prefix` (`string`, optional): Only list folders whose names start with this text. Example: reports/

Example input: `{"bucket":"<bucket>"}`

### `googlecloudstorage_notifications_list`

List Notifications · Read-only

List the Pub/Sub notification configurations of a Cloud Storage bucket.
Returns each configuration's id, topic, event_types, payload_format and object_name_prefix.
Use this to see where bucket change events are sent.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports

Example input: `{"bucket":"<bucket>"}`

### `googlecloudstorage_object_download`

Download Object · Read-only

Download the content of an object in a Cloud Storage bucket.
Returns the raw file content as the response body, not JSON; text files such as CSV, JSON or logs come back as text.
Use this to read a file. Use googlecloudstorage_object_get for metadata only. Large or binary files may not be usable in the response.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `object` (`string`, required): Full name of the object inside the bucket. URL-encode the name: write / as %2F and a space as %20. Example: reports%2F2026%2Fq1.csv for reports/2026/q1.csv
- `generation` (`string`, optional): Specific version (generation number) of the object. Omit it for the live version. Example: 1700000000000000

Example input: `{"bucket":"<bucket>","object":"<object>"}`

### `googlecloudstorage_object_get`

Get Object Metadata · Read-only

Get the metadata of one object in a Cloud Storage bucket.
Returns its name, size, contentType, md5Hash, crc32c, generation, metageneration, timestamps and custom metadata, but not the file content.
Use this to inspect a file. Use googlecloudstorage_object_download to read its content.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `object` (`string`, required): Full name of the object inside the bucket. URL-encode the name: write / as %2F and a space as %20. Example: reports%2F2026%2Fq1.csv for reports/2026/q1.csv
- `generation` (`string`, optional): Specific version (generation number) of the object. Omit it for the live version. Example: 1700000000000000

Example input: `{"bucket":"<bucket>","object":"<object>"}`

### `googlecloudstorage_objects_list`

List Objects · Read-only

List the objects (files) in a Cloud Storage bucket, optionally under a folder-like prefix.
Returns each object's name, size, contentType, updated time, generation and md5Hash, plus prefixes (sub-folders, when delimiter is /) and nextPageToken.
Use this to browse a bucket. Use googlecloudstorage_object_get for one object's metadata.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `delimiter` (`string`, optional): Set to / to list one folder level: deeper names are returned in prefixes instead of items. Example: /
- `match_glob` (`string`, optional): Glob pattern the object names must match. Example: **.csv
- `max_results` (`integer`, optional): Maximum number of objects per page. Example: 100
- `page_token` (`string`, optional): nextPageToken from the previous page. Example: CgdyZXBvcnRz
- `prefix` (`string`, optional): Only list objects whose names start with this text, such as a folder path. Not URL-encoded. Example: reports/2026/
- `soft_deleted` (`boolean`, optional): List only soft-deleted objects, which googlecloudstorage_object_restore can bring back. Cannot be combined with versions. Example: false
- `versions` (`boolean`, optional): Also list old (noncurrent) versions of objects. Example: false

Example input: `{"bucket":"<bucket>"}`

### `googlecloudstorage_service_account_get`

Get Service Agent · Read-only

Get the email of the Cloud Storage service agent for a Google Cloud project.
Returns email_address.
Use this to grant the service agent access, for example the Pub/Sub Publisher role before googlecloudstorage_notification_create.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `project` (`string`, required): Google Cloud project ID or number. Example: my-project-123

Example input: `{"project":"<project>"}`

### `googlecloudstorage_bucket_create`

Create Bucket · Write

Create a Cloud Storage bucket in a Google Cloud project.
Returns the new bucket resource.
Use this to add a bucket. Bucket names are globally unique; the call fails with 409 if the name is taken.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `name` (`string`, required): Globally unique bucket name: 3 to 63 lowercase letters, digits, dashes, underscores and dots. Example: acme-reports-2026
- `project` (`string`, required): Google Cloud project ID or number. Example: my-project-123
- `labels` (`object`, optional): Key-value labels for the bucket. Keys and values are lowercase. Example: {"team": "finance"}
- `lifecycle_rules` (`array`, optional): Lifecycle rules that replace the bucket's current rules. Each rule has an action (Delete, SetStorageClass or AbortIncompleteMultipartUpload) and a condition, such as age in days. Example: [{"action": {"type": "Delete"}, "condition": {"age": 365}}]
- `location` (`string`, optional): Where the bucket's data lives: a region, dual-region or multi-region. It cannot be changed later. Defaults to US. Example: EUROPE-WEST1
- `storage_class` (`string`, optional): Default storage class for new objects: STANDARD, NEARLINE, COLDLINE or ARCHIVE. Example: STANDARD. One of: `STANDARD`, `NEARLINE`, `COLDLINE`, `ARCHIVE`.
- `uniform_bucket_level_access` (`boolean`, optional): Control access with IAM only, turning off per-object ACLs. Example: true
- `versioning_enabled` (`boolean`, optional): Keep old versions of objects when they are overwritten or deleted. Example: true

Example input: `{"name":"<name>","project":"<project>"}`

### `googlecloudstorage_bucket_update`

Update Bucket · Write

Change settings of a Cloud Storage bucket: storage class, labels, versioning, uniform access or lifecycle rules.
Returns the updated bucket.
Use this to change a bucket. Only the fields you pass are changed; labels you pass replace the matching keys.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `labels` (`object`, optional): Key-value labels for the bucket. Keys and values are lowercase. Example: {"team": "finance"}
- `lifecycle_rules` (`array`, optional): Lifecycle rules that replace the bucket's current rules. Each rule has an action (Delete, SetStorageClass or AbortIncompleteMultipartUpload) and a condition, such as age in days. Example: [{"action": {"type": "Delete"}, "condition": {"age": 365}}]
- `storage_class` (`string`, optional): Default storage class for new objects: STANDARD, NEARLINE, COLDLINE or ARCHIVE. Example: STANDARD. One of: `STANDARD`, `NEARLINE`, `COLDLINE`, `ARCHIVE`.
- `uniform_bucket_level_access` (`boolean`, optional): Control access with IAM only, turning off per-object ACLs. Example: true
- `versioning_enabled` (`boolean`, optional): Keep old versions of objects when they are overwritten or deleted. Example: true

Example input: `{"bucket":"<bucket>"}`

### `googlecloudstorage_folder_create`

Create Folder · Write

Create a folder in a Cloud Storage bucket that has hierarchical namespace enabled.
Returns the new folder.
Use this only for hierarchical-namespace buckets; in other buckets folders are just name prefixes.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `name` (`string`, required): Folder name, ending with /. Example: reports/2027/
- `recursive` (`boolean`, optional): Also create missing parent folders. Example: true

Example input: `{"bucket":"<bucket>","name":"<name>"}`

### `googlecloudstorage_notification_create`

Create Notification · Write

Send change events from a Cloud Storage bucket to a Pub/Sub topic.
Returns the new notification configuration with its id.
Use this to get notified when objects are created, deleted or updated.
The bucket's Cloud Storage service agent (from googlecloudstorage_service_account_get) needs the Pub/Sub Publisher role on the topic.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `payload_format` (`string`, required): Message content: JSON_API_V1 (object metadata as JSON) or NONE. Example: JSON_API_V1. One of: `JSON_API_V1`, `NONE`.
- `topic` (`string`, required): Pub/Sub topic to publish to, in the form //pubsub.googleapis.com/projects/PROJECT/topics/TOPIC. Example: //pubsub.googleapis.com/projects/my-project-123/topics/gcs-events
- `event_types` (`array`, optional): Only send these events: OBJECT_FINALIZE, OBJECT_METADATA_UPDATE, OBJECT_DELETE or OBJECT_ARCHIVE. Omit to send all. Example: ["OBJECT_FINALIZE"]
- `object_name_prefix` (`string`, optional): Only send events for objects whose names start with this text. Example: uploads/

Example input: `{"bucket":"<bucket>","payload_format":"JSON_API_V1","topic":"<topic>"}`

### `googlecloudstorage_object_compose`

Compose Objects · Write

Concatenate up to 32 objects in the same bucket into one new object.
Returns the metadata of the composed object.
Use this to join file parts, such as log chunks, into one file.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `destination_object` (`string`, required): Name of the object to create. URL-encode the name: write / as %2F and a space as %20. Example: logs%2Fday.log
- `source_object_names` (`array`, required): Names of the objects to join, in order, all in the same bucket. Plain names, not URL-encoded. Example: ["logs/part-1.log", "logs/part-2.log"]
- `content_type` (`string`, optional): MIME type of the joined object. Example: text/plain

Example input: `{"bucket":"<bucket>","destination_object":"<destination_object>","source_object_names":["logs/part-1.log","logs/part-2.log"]}`

### `googlecloudstorage_object_copy`

Copy Object · Write

Copy an object to a new name, in the same bucket or another bucket.
Returns the metadata of the new object.
Use this to duplicate a file. Use googlecloudstorage_object_move to rename within a bucket.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `destination_bucket` (`string`, required): Bucket to copy into. Example: acme-archive
- `destination_object` (`string`, required): Name for the copy. URL-encode the name: write / as %2F and a space as %20. Example: 2026%2Fq1.csv
- `source_bucket` (`string`, required): Bucket that holds the object to copy. Example: acme-reports
- `source_object` (`string`, required): Name of the object to copy. URL-encode the name: write / as %2F and a space as %20. Example: reports%2Fq1.csv
- `if_generation_match` (`string`, optional): Only make the change if the object's current generation matches this value. Use 0 to only write when the destination does not exist yet. Example: 0

Example input: `{"destination_bucket":"<destination_bucket>","destination_object":"<destination_object>","source_bucket":"<source_bucket>","source_object":"<source_object>"}`

### `googlecloudstorage_object_move`

Move Object · Write

Rename (move) an object within a Cloud Storage bucket.
Returns the metadata of the object under its new name.
Use this to rename or move a file inside one bucket. Use googlecloudstorage_object_copy to copy to another bucket.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `destination_object` (`string`, required): New name of the object. URL-encode the name: write / as %2F and a space as %20. Example: reports%2Fq1.csv
- `source_object` (`string`, required): Current name of the object. URL-encode the name: write / as %2F and a space as %20. Example: inbox%2Fq1.csv
- `if_generation_match` (`string`, optional): Only make the change if the object's current generation matches this value. Use 0 to only write when the destination does not exist yet. Example: 0

Example input: `{"bucket":"<bucket>","destination_object":"<destination_object>","source_object":"<source_object>"}`

### `googlecloudstorage_object_restore`

Restore Object · Write

Restore a soft-deleted object in a Cloud Storage bucket.
Returns the metadata of the restored object.
Use this to undo a delete within the bucket's soft-delete window. List soft-deleted objects with googlecloudstorage_objects_list to get the generation.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `generation` (`string`, required): Generation of the soft-deleted object to restore. Example: 1700000000000000
- `object` (`string`, required): Full name of the object inside the bucket. URL-encode the name: write / as %2F and a space as %20. Example: reports%2F2026%2Fq1.csv for reports/2026/q1.csv

Example input: `{"bucket":"<bucket>","generation":"<generation>","object":"<object>"}`

### `googlecloudstorage_object_update`

Update Object Metadata · Write

Change the metadata of an object in a Cloud Storage bucket, such as its content type, cache control or custom metadata.
Returns the updated object metadata.
Use this to change how a file is served or tagged. The file content is not changed.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `object` (`string`, required): Full name of the object inside the bucket. URL-encode the name: write / as %2F and a space as %20. Example: reports%2F2026%2Fq1.csv for reports/2026/q1.csv
- `cache_control` (`string`, optional): Cache-Control header served with the object. Example: public, max-age=3600
- `content_disposition` (`string`, optional): Content-Disposition header served with the object. Example: attachment; filename="q1.csv"
- `content_type` (`string`, optional): MIME type of the object. Example: text/csv
- `metadata` (`object`, optional): Custom key-value metadata to set on the object. Set a key to null to remove it. Example: {"owner": "finance"}

Example input: `{"bucket":"<bucket>","object":"<object>"}`

### `googlecloudstorage_bucket_delete`

Delete Bucket · Destructive

Delete an empty Cloud Storage bucket.
Returns no content on success; fails with 409 if the bucket still holds objects.
Use this to remove a bucket after deleting its objects with googlecloudstorage_object_delete.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports

Example input: `{"bucket":"<bucket>"}`

### `googlecloudstorage_notification_delete`

Delete Notification · Destructive

Delete a Pub/Sub notification configuration from a Cloud Storage bucket.
Returns no content on success. The Pub/Sub topic is not deleted.
Use this to stop sending bucket events to a topic.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `notification_id` (`string`, required): ID of the notification configuration. Get it from googlecloudstorage_notifications_list. Example: 5

Example input: `{"bucket":"<bucket>","notification_id":"<notification_id>"}`

### `googlecloudstorage_object_delete`

Delete Object · Destructive

Delete an object from a Cloud Storage bucket.
Returns no content on success. If the bucket has versioning or soft delete, the object can still be restored.
Use this to remove a file. Use googlecloudstorage_object_restore to bring back a soft-deleted object.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `bucket` (`string`, required): Name of the bucket, without gs://. Example: acme-reports
- `object` (`string`, required): Full name of the object inside the bucket. URL-encode the name: write / as %2F and a space as %20. Example: reports%2F2026%2Fq1.csv for reports/2026/q1.csv
- `generation` (`string`, optional): Specific version (generation number) of the object. Omit it for the live version. Example: 1700000000000000

Example input: `{"bucket":"<bucket>","object":"<object>"}`

## Related

Other Files & Documents connectors ([all 76](/agentkit/connectors/?category=files-documents)):

- [Notion](/agentkit/connectors/notion/): Scalekit connector, OAuth, 51 tools
- [Google Sheets](/agentkit/connectors/googlesheets/): Scalekit connector, OAuth, 48 tools
- [Google Drive](/agentkit/connectors/googledrive/): Scalekit connector, OAuth, 47 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
