Google cloud vision MCP integration
Runs OCR and image annotation over pictures and PDFs, builds the Product Search catalogue, and polls long-running batch operations.
29actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Annotate files with vision API
Lyro analyzes customer-submitted images to identify visual issues. Your team diagnoses problems from screenshots alone, saving customers time describing them.
Async batch annotate files
Lyro processes multiple customer images at scale to extract data. Your team handles bulk image uploads efficiently without blocking the conversation thread.
Add product to productset
Lyro catalogs products for visual search matching. Customers find the exact product they're asking about by showing a photo instead of describing it.
How businesses use Google cloud vision + Lyro
Each card is one request a support team gets, and the Google cloud vision actions Lyro runs to close it.
Read what is inside an image or a document
Lyro sends a batch of images or PDFs for annotation and returns the detections in one pass, so text extracted from a scanned receipt or a label read off a photo is available in the conversation that asked.
Annotate ImagesAnnotate Files with Vision APIAnnotate Location ImagesBuild a catalogue for visual product search
Lyro creates the product, groups it into the product set it belongs to, and attaches the reference image a match will be made against, so a new item becomes findable by picture rather than by SKU alone.
Create Vision ProductCreate Product SetCreate ReferenceImageKeep the product index from going stale
Lyro links a product into another set, corrects the display name and labels that drive filtering, and clears the orphans left behind by deleted items, so search results reflect the live catalogue.
Add Product to ProductSetUpdate ProductPurge ProductsFollow an asynchronous batch to completion
Lyro submits a large file batch, polls the operation it returns, and cancels one that is no longer wanted, so a job too big for a synchronous call still has a reported outcome.
Async Batch Annotate FilesGet Vision API OperationCancel Vision Operation
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Google cloud vision actions it has and picks the ones a request needs.
- 01
Connect Google cloud vision
Authorize the Google cloud vision account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
- 02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Google cloud vision actions that close it and chains as many as the request needs.
- 03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free
Everything else about Google cloud vision
Setup, permissions, and the limits of what Lyro can do inside Google cloud vision.
Both, through different actions. Annotate Images handles image formats, while Annotate Files with Vision API covers PDF, TIFF, and GIF input, and Async Batch Annotate Files is the route for documents large enough that a synchronous call would time out before returning.
Every action available in Google cloud vision
All 29 actions your agent can call on Google cloud vision, straight from the live MCP connection.
Annotate files with vision API
Perform image detection and annotation for batch files in Google Cloud Vision.
Async batch annotate files
Run asynchronous image detection and annotation for a list of generic files (PDF, TIFF, GIF).
Annotate images
Run image detection and annotation for a batch of images using Google Cloud Vision API.
Annotate images async batch
Run asynchronous image detection and annotation for a batch of images.
Annotate location images
Run image detection and annotation for a batch of images scoped to a specific project and location.
Create vision product
Creates a new Product resource in Google Cloud Vision Product Search.
Create product set
Creates a new ProductSet resource in Google Cloud Vision Product Search.
Create referenceimage
Create a ReferenceImage under a product.
Delete product
Permanently deletes a Product and its associated reference images from Google Cloud Vision API.
Get product
Get information associated with a Product.
Get product set
Get a ProductSet.
Import product sets
Asynchronously imports product sets and reference images from a CSV file stored in Google Cloud Storage.
List vision AI indexendpoints
Lists IndexEndpoints in Vertex AI Vision for a given project and location.
List locations
List available Vision AI service locations for a project.
List vision API operations
List operations that match the specified filter.
Purge products
Asynchronously delete products in a ProductSet or orphan products.
Update product
Update a Product's mutable fields: displayName, description, and productLabels.
Update product set
Update a ProductSet resource.
Add product to productset
Add a Product to a ProductSet in Google Cloud Vision Product Search.
Cancel vision operation
Starts asynchronous cancellation of a long-running Vision API operation.
Delete vision API operation
Delete a long-running Vision API operation.
Delete product set
Permanently delete a ProductSet.
Delete reference image
Permanently removes a reference image from a product in Google Cloud Vision Product Search.
Get vision API operation
Retrieves the latest state of a long-running Vision API operation.
Get reference image
Get information associated with a ReferenceImage.
List products in productset
List Products in a specified ProductSet.
List projects
List Google Cloud projects accessible to the authenticated user via Cloud Resource Manager API.
List reference images
List reference images for a product.
Remove product from productset
Removes a Product from a specified ProductSet in Google Cloud Vision API.
The tools Google cloud vision sits next to
Same connection, same setup. Pick the next one your team already uses.
Bigml
Inventories models, clusters, and anomaly detectors, reads their evaluations and predictions, and sets up projects and external data connectors.
DeepSeek
Sends prompts to deepseek-chat or deepseek-reasoner with tool calling and thinking mode, and checks balance and model availability first.
Jigsawstack
Reads text out of customer attachments, translates and voices replies, and screens submitted text and images before they reach the queue.
Ollama
Route a request to a self-hosted model, reuse OpenAI-format endpoints against it, and report which models the host currently has installed.
RunPod
Reports GPU availability and pricing, provisions clusters and serverless endpoints, and stores the registry credentials a private image needs.
Veo
Submits a prompt as a Veo generation job, tracks the operation until it finishes, and downloads the finished clip.
Ready to connect Google cloud vision?
Authorize the account and your agent has all 29 actions from the first conversation.