What can you do with the Google Cloud Vision integration?

LiveContext exposes 27 operations on Google Cloud Vision, covering product, product set, operation and reference image. Common uses include automate product management, automate product set management and automate operation management.

Which OAuth scopes does Google Cloud Vision require?

The operations that declare a scope all need https://www.googleapis.com/auth/cloud-vision.

LiveContext

All integrations

Google Cloud Vision integration

Google Cloud Vision AI API for analyzing images with machine learning. Detect objects, faces, text (OCR), labels, landmarks, logos, explicit content, and image properties. Supports batch processing, product search, and web detection.

27 toolsOAuthAPI docs

Connect Google Cloud Vision How integrations work

Common Google Cloud Vision use cases

automate product management
automate product set management
automate operation management
automate reference image management
get product programmatically
list product programmatically
get operation programmatically
purge product programmatically
create product programmatically
delete product programmatically

What you can do with Google Cloud Vision

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Product, 6 operations

POSTcreate_product
Create a new product resource for Vision Product Search. A product represents a physical item with reference images and key-value labels for filtering.
DELETEdelete_product
Delete a product permanently. Also removes all reference images associated with the product.
GETget_product
Get details of a specific product by its ID, including display name, description, category, and labels.
GETlist_products
List all products in the specified project and location. Returns paginated results.
POSTpurge_products
Bulk-delete products from a project and location, either all products in a product set or all orphan products. Returns a long-running operation.
PATCHupdate_product
Update an existing product's metadata. Only the fields specified in the updateMask are modified. Use this to change display name, description, category, or labels.

Product set, 6 operations

POSTcreate_product_set
Create a new product set for organizing products used in Vision Product Search. Product sets group products that can be searched together.
DELETEdelete_product_set
Delete a product set permanently. Does not delete the products within the set; they must be deleted separately.
GETget_product_set
Get details of a specific product set by its ID.
POSTimport_product_sets
Bulk-import products, reference images and product-set memberships from a CSV file stored in Google Cloud Storage. Returns a long-running operation.
GETlist_product_sets
List all product sets in the specified project and location. Returns paginated results.
PATCHupdate_product_set
Update an existing product set's metadata. Only the fields specified in the updateMask are modified.

Operation, 4 operations

POSTcancel_operation
Cancel a long-running async operation. Best-effort cancellation; the operation may still complete if it is close to finishing.
DELETEdelete_operation
Delete a long-running operation record. This only removes the client's record of the operation; it does not cancel the underlying work.
GETget_operation
Get the status and result of a long-running operation returned by async batch annotation endpoints. Poll this endpoint to check if an async operation has completed.
GETlist_operations
List long-running operations that match optional filters. Use to monitor or audit async batch annotation jobs.

Reference image, 4 operations

POSTcreate_reference_image
Create a reference image for a product. Reference images are used by Vision Product Search to match query images against products. Each product can have multiple reference images.
DELETEdelete_reference_image
Delete a reference image permanently. The image is removed from the product and will no longer be used for product search matching.
GETget_reference_image
Get details of a specific reference image belonging to a product, including its Google Cloud Storage URI and bounding polygons.
GETlist_reference_images
List all reference images associated with a specific product. Returns paginated results.

Annotate file, 1 operation

POSTannotate_files
Analyze files such as PDFs and TIFFs that may contain multiple pages. Performs synchronous annotation on a small batch of files with inline response. Supports the same detection features as image annotation.

Annotate image, 1 operation

POSTannotate_images
Analyze images using one or more Vision AI features. Send images with desired detection types to get annotations such as labels, text, faces, objects, landmarks, logos, and more. This is the primary endpoint for all image analysis tasks.

Async batch annotate file, 1 operation

POSTasync_batch_annotate_files
Run asynchronous file annotation on a batch of PDF or TIFF files and write output to Google Cloud Storage. Returns a long-running operation that can be polled for completion.

Async batch annotate image, 1 operation

POSTasync_batch_annotate_images
Run asynchronous image detection on a batch of images and write output to Google Cloud Storage. Use for large-scale processing where results are stored as JSON in a GCS bucket. Returns a long-running operation.

Product from product set, 1 operation

POSTremove_product_from_product_set
Remove a product from a product set. The product itself is not deleted, only the association with the product set is removed.

Product to product set, 1 operation

POSTadd_product_to_product_set
Add an existing product to a product set. A product can belong to multiple product sets. The product and product set must be in the same location.

Products in product set, 1 operation

GETlist_products_in_product_set
List the products that belong to a specific product set. Returns paginated results.

OAuth scopes Google Cloud Vision requires

Each operation declares the scopes Google Cloud Vision requires for it.

https://www.googleapis.com/auth/cloud-visionneeded by add_product_to_product_set, annotate_files, annotate_images and 24 more

Use Google Cloud Vision from Claude Code, Cursor or Codex

Connect Google Cloud Vision in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Google Cloud Vision operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Google Cloud Vision

Create your workspace
Sign up free. Nothing to install.
Connect Google Cloud Vision once
Add your Google Cloud Vision connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Google Cloud Vision integration FAQ

What can you do with the Google Cloud Vision integration?: LiveContext exposes 27 operations on Google Cloud Vision, covering product, product set, operation and reference image. Common uses include automate product management, automate product set management and automate operation management.
Which OAuth scopes does Google Cloud Vision require?: The operations that declare a scope all need https://www.googleapis.com/auth/cloud-vision.