Inventories models, clusters, and anomaly detectors, reads their evaluations and predictions, and sets up projects and external data connectors.
45actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Ayro sets up a new machine learning project in BigML to organize and train models for your customer service use case. This creates a workspace for predictive insights.
Ayro retrieves results from batch prediction runs in BigML, showing which customer segments or behaviors the model identified. This surfaces actionable ML insights.
Ayro removes completed or obsolete machine learning projects from BigML to keep your workspace clean and reduce costs. This prevents clutter in your ML infrastructure.
Each card is one request a support team gets, and the Bigml actions Ayro runs to close it.
Ayro lists the models, ensembles, deepnets, and fusions an account holds and pulls the evaluations recorded against them, so a question about which model scored best is answered from BigML's own results.
Ayro reads single predictions, the batch jobs behind bulk scoring, and time series forecasts, so a question about whether a scoring run happened has an answer without opening the dashboard.
Ayro lists clusters, anomaly detectors, topic models, associations, and PCAs, so segmentation and outlier work that was built once and forgotten resurfaces before someone rebuilds it.
Ayro creates the project a body of work belongs to, updates the source behind a dataset, and registers an external connector so BigML can reach a database it could not before.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Bigml actions it has and picks the ones a request needs.
Authorize the Bigml 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 Bigml 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 freeBigml · Ayro
What can you do in Bigml 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 Bigml.
Not through this toolkit. The action list is built for inspection and organisation - it lists and reads models, ensembles, deepnets, clusters, evaluations, predictions, and forecasts, and its only writes are Create Project, Update Source, Create External Connector, and Delete Project. Training and scoring stay in BigML; the integration reports on what is already there.
All 45 actions your agent can call on Bigml, straight from the live MCP connection.
Create a new external connector for data sources.
Create a new project.
Delete an existing project.
Retrieves complete details of a BigML configuration by its ID to get stored parameters.
Retrieves complete details of a BigML external connector by its ID.
Retrieve details of a project by ID.
Retrieves complete details of a BigML source by its ID.
List anomaly detector resources in your account.
List anomaly score resources.
List association resources.
List association set resources in your account.
List batch anomaly score resources.
List all batch centroid resources in your account with support for filtering, ordering, and pagination.
List batch prediction resources.
List batch projection resources with support for filtering, ordering, and pagination.
List batch topic distribution resources.
List centroid resources.
List cluster resources with support for filtering, ordering, and pagination.
List composite source resources.
List all configuration resources in your account.
List correlation resources.
List dataset resources.
List deep neural network resources.
List ensemble resources with filtering, ordering, and pagination support.
List evaluation resources.
List execution resources.
List forecast resources.
List fusion resources.
List WhizzML library resources.
List linear regression resources.
Same connection, same setup. Pick the next one your team already uses.
Compares model pricing and limits, parses documents, transcribes audio, redacts personal data, and reports what past calls cost.
Submits enhancement jobs, tracks them by hash, returns the finished result URL, and clears stored images once they are delivered.
Vets a model's card and security scan before adoption, runs inference, commits to Hub repositories, and watches repos through webhooks.
Lists 3D and AR embeds, orders modeling jobs, and reports completion percentage on the ones already in progress.
Detects the language an incoming message is written in and scores how closely two names or two addresses match before anything is acted on.
Opens calls with their cost and duration, changes assistant voice and model settings, provisions phone numbers, and runs call analytics.

Authorize the account and your agent has all 45 actions from the first conversation.
