Google Cloud Vision for AI agents

Google Cloud Vision analyzes images for labels, faces, landmarks, text, and explicit content, giving apps computer-vision capabilities via API. Teams building AI products use it to add this capability without training or hosting their own model. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

AI and modelsAPI keyMCP + RESTcloud.google.com
AUDIT LOG · GOOGLE CLOUD VISIONPOLICY: acme-support
09:41:07 · claude · u_8f2read
google_cloud_vision.list_locations
List Locations✓ allowed · 212ms
09:41:08 · claude · u_8f2read
google_cloud_vision.get_product
Get Product✓ allowed · 164ms
09:41:09 · claude · u_8f2write
google_cloud_vision.create_product
Create Vision Product✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
google_cloud_vision.delete_product
Delete Product✕ blocked · policy: deny
EVERY GOOGLE CLOUD VISION CALL, ON THE RECORD
01 · USE CASES

What agents do in Google Cloud Vision.

01

Extract text from an image

Run OCR on a scanned receipt or document image to pull out the text for a record.

02

Label objects in a photo

Get label annotations for an uploaded photo to auto-tag it in a media library.

03

Check content before publishing

Screen an image for explicit content, read-only, before it is approved for publishing.

02 · ACTIONS

29 Google Cloud Vision actions, graded by risk.

Every Google Cloud Vision action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

5

Look things up. Allowed by default.

  • google_cloud_vision.get_product
    Get Product
  • google_cloud_vision.list_locations
    List Locations
  • google_cloud_vision.get_product_set
    Get Product Set
  • google_cloud_vision.list_operations
    List Vision API Operations
  • google_cloud_vision.list_index_endpoints
    List Vision AI IndexEndpoints

write

17

Create and change things. Allow, or ask the user first.

  • google_cloud_vision.create_product
    Create Vision Product
  • google_cloud_vision.update_product
    Update Product
  • google_cloud_vision.create_product_set
    Create Product Set
  • google_cloud_vision.update_product_set
    Update Product Set
  • google_cloud_vision.create_reference_image
    Create ReferenceImage
  • google_cloud_vision.annotate_files
    Annotate Files with Vision API
  • google_cloud_vision.annotate_images
    Annotate Images
  • google_cloud_vision.import_product_sets
    Import Product Sets
  • google_cloud_vision.vision_get_operation
    Get Vision API Operation
  • google_cloud_vision.vision_list_projects
    List Projects
  • google_cloud_vision.annotate_location_images
    Annotate Location Images
  • google_cloud_vision.annotate_files_async_batch
    Async Batch Annotate Files
  • google_cloud_vision.vision_get_reference_image
    Get Reference Image
  • google_cloud_vision.annotate_images_async_batch
    Annotate Images Async Batch
  • google_cloud_vision.vision_list_reference_images
    List Reference Images
  • google_cloud_vision.vision_add_product_to_product_set
    Add Product to ProductSet
+ 1 MORE

destructive

7

Delete, cancel or archive. Ask first, or deny outright.

  • google_cloud_vision.delete_product
    Delete Product
  • google_cloud_vision.purge_products
    Purge Products
  • google_cloud_vision.vision_cancel_operation
    Cancel Vision Operation
  • google_cloud_vision.vision_delete_operation
    Delete Vision API Operation
  • google_cloud_vision.vision_delete_product_set
    Delete Product Set
  • google_cloud_vision.vision_delete_reference_image
    Delete Reference Image
  • google_cloud_vision.vision_remove_product_from_product_set
    Remove Product from ProductSet
03 · HOW IT WORKS

Google Cloud Vision in three steps.

  1. 01Your users connect Google Cloud VisionThey add their Google Cloud Vision api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Vision Product” can wait for the user, and “delete Product” can be denied outright.
  3. 03Any agent can actYour agent calls Google Cloud Vision through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('google_cloud_vision', {
  read: 'allow',
  write: 'ask',        // create_product
  destructive: 'deny',  // delete_product
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Google Cloud Vision connects.

Users add their Google Cloud Vision api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Google Cloud Vision connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Google Cloud Vision from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Google Cloud Vision and Arc0, answered.

Q01

Can I use Google Cloud Vision with Claude, ChatGPT or Cursor?

Yes. Connect Google Cloud Vision to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Google Cloud Vision actions you allow.

Q02

How do users connect Google Cloud Vision?

Users add their Google Cloud Vision api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Google Cloud Vision actions can my agent take?

29 in total: 5 read, 17 write and 7 destructive, such as “create Vision Product”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Google Cloud Vision?

Yes. Actions like “delete Product” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Google Cloud Vision too?

Yes. The same Google Cloud Vision connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Google Cloud Vision into your agent.

Your users connect Google Cloud Vision once, under your brand. Your agent gets 29 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan