Creates image, video, LiDAR, and text annotation tasks, batches and finalizes them, reports completion counts, and reassigns Studio projects.
41actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Ayro creates an image annotation task in Scale AI where workers label images with geometric shapes. The team builds training data for computer vision models efficiently.
Ayro retrieves detailed information about a specific annotation task including status and results. The customer sees quality scores and progress without logging into Scale AI.
Ayro uploads a local file to Scale AI with up to 80 MB per file for annotation. The file is queued for worker assignment and processing begins immediately.
Each card is one request a support team gets, and the Scale.ai actions Ayro runs to close it.
Ayro creates the right task type for the job - geometric shapes on images, objects tracked across video frames, or entity mentions highlighted in text - against the project it belongs to.
Ayro reports a batch's current status with its task completion counts, lists the batches on a project newest first, and opens a single task to check its parameters and returned results.
Ayro reorders the pending batches in Studio, assigns projects to specific team members, and reads back who is currently on what before anything else gets queued behind it.
Ayro sets the ontology defining the labels tasks reference and the default parameters new tasks inherit, and re-sends a callback when a completed task never reached your endpoint.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Scale.ai actions it has and picks the ones a request needs.
Authorize the Scale.ai account your team already uses — one consent screen, no API keys, no mapping tables. Ayro can only do what you granted that account, and you can disconnect it at any time.
Describe the job the way you would hand it to a teammate. Ayro maps it to the Scale.ai actions that close it and chains as many as the request needs.
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 freeScale.ai · Ayro
What can you do in Scale.ai without me setting anything up?
These, right away:
Great, let's start with the first one.
FAQ
Setup, permissions, and the limits of what Ayro can do inside Scale.ai.
Two ways. Upload File pushes a local file to Scale's servers with a limit of 80 MB per file, and Import File pulls from an external URL instead, which is the route for anything larger or already hosted. Get Assets then lists what is there, filtered by project and metadata.
All 41 actions your agent can call on Scale.ai, straight from the live MCP connection.
Add project assignments to team members in Scale AI Studio.
Add tags to an existing task.
Create a new batch within a project.
Create a document transcription task where workers transcribe and annotate information from single or multi-page documents.
Create an image annotation task where annotators label images with vector geometric shapes (box, polygon, line, point, cuboid, ellipse).
Create a lidar annotation task where annotators mark objects with 3D cuboids in 3D space.
Create a LiDAR segmentation task where annotators assign semantic class labels to individual LiDAR points.
Create a named entity recognition task for labelers to highlight text entity mentions.
Create a segmentation task where annotators classify pixels in an image according to provided labels.
Create a textcollection task for collecting information from attachments and/or web sources.
Create a video annotation task where annotators draw geometric shapes around specified objects across video frames.
Create a video playback annotation task where annotators draw shapes around specified objects in video files.
Remove specified tags from a Scale AI task.
Remove the unique identifier from a task.
Finalize a batch so its tasks can be worked on.
Retrieve file assets with filtering capabilities by project and metadata.
Retrieve the details of a batch with the specified name.
Retrieve the current status of a batch and task completion counts.
Retrieve fixless audits by task ID or audit ID.
Retrieve details about a specific Scale AI project using its unique identifier.
Retrieve training attempts matching provided filter parameters.
Retrieve current project assignments of all active team users in Scale AI Studio.
Retrieve basic information about all pending batches in Studio.
Retrieve detailed information about a specific task in Scale AI.
Retrieve basic information about all team members associated with the account.
Retrieve detailed information about a specific task using its task ID.
Retrieve secure authenticated task response data.
Import files from an external URL endpoint into Scale's system rather than uploading directly from local storage.
Invite users by email to team with specified role.
Retrieve all batches in descending order by creation date.
Same connection, same setup. Pick the next one your team already uses.
Sends approved WhatsApp templates, reads campaign and contact analytics, maintains contacts and tags, and reacts to Shopify cart and order events.
Reports voices and character usage, builds conversational agents with indexed knowledge bases, tunes pronunciation, and queues outbound batch calls.
Reads text out of customer attachments, translates and voices replies, and screens submitted text and images before they reach the queue.
Route a request to a self-hosted model, reuse OpenAI-format endpoints against it, and report which models the host currently has installed.
Reports GPU availability and pricing, provisions clusters and serverless endpoints, and stores the registry credentials a private image needs.
Scores a submitted passage for AI authorship, checks it for plagiarism against online sources, and measures how closely two texts match.

Authorize the account and your agent has all 41 actions from the first conversation.
