Databox MCP integration
Creates Databox data sources and datasets, pushes records into them, verifies each ingestion landed, and removes what is no longer feeding a dashboard.
7actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Push data to dataset (v1)
Ayro sends data points to a Databox dataset for visualization and tracking. Your team logs metrics and KPIs into dashboards without manual entry.
Create data source
Ayro sets up a new data source in Databox during a conversation. Your team can instantly create analytics pipelines without leaving chat.
Get dataset ingestion status
Ayro checks the status of a specific data ingestion to a dataset. Your team monitors pipeline health and debugs failed data loads.
How businesses use Databox + Ayro
Each card is one request a support team gets, and the Databox actions Ayro runs to close it.
Set up a data source and its first dataset
Ayro finds the account ID, creates the data source with its title and timezone, then creates a dataset inside it with the primary keys that identify a unique record.
List AccountsCreate Data SourceCreate DatasetPush a batch of records into a dataset
Ayro sends an array of records matching the dataset schema into the dataset by ID, so a number that changed in a source system reaches the dashboard reading from it.
Push Data To DatasetCreate DatasetList AccountsConfirm an ingestion actually landed
Ayro takes the ingestion ID returned by the push and checks its status against the dataset, so a silent failure is caught rather than showing up as a dashboard that quietly stopped moving.
Get Dataset Ingestion StatusPush Data To DatasetList AccountsRetire datasets and sources that are finished
Ayro removes a dataset that no longer feeds anything, or the whole data source when a tool is decommissioned, keeping the account free of feeds nobody reads.
Delete DatasetDelete Data SourceList Accounts
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Databox actions it has and picks the ones a request needs.
Connect Databox
Authorize the Databox 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.
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Ayro maps it to the Databox actions that close it and chains as many as the request needs.
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
Databox · Ayro
What can you do in Databox without me setting anything up?
These, right away:
- Create dataset
- Get dataset ingestion status
- Delete dataset
Great, let's start with the first one.
FAQ
Everything else about Databox
Setup, permissions, and the limits of what Ayro can do inside Databox.
No. Every action in this toolkit sits on the ingestion side: List Accounts, Create Data Source, Create Dataset, Push Data to Dataset, Get Dataset Ingestion Status, Delete Dataset, and Delete Data Source. Ayro feeds the dashboards and verifies the feed arrived; reading a metric back is still done in Databox.
Every action available in Databox
All 7 actions your agent can call on Databox, straight from the live MCP connection.
Create dataset
Create a new dataset in Databox data source.
Create data source
Create a new data source in Databox.
Delete dataset
Delete a dataset by ID in Databox.
Delete data source
Delete a data source by ID in Databox.
Get dataset ingestion status
Check the status of a specific data ingestion for a dataset.
List accounts
Retrieve all Databox accounts accessible to the authenticated user.
Push data to dataset (v1)
Push data points to a Databox dataset using the v1 API.
The tools Databox sits next to
Same connection, same setup. Pick the next one your team already uses.
Builtwith
Profiles a domain's current and historical stack, finds every site running a given technology, and packages the result as a domain list.
Felt
Reports a map's layers and elements, adds or updates features as GeoJSON, organises maps into projects, and clones maps as templates.
LeadBoxer
Pulls a lead's sessions and event history, retags records as qualification changes, and logs conversions back from the conversation.
Parsehub
Retrieves every scraping project on a ParseHub account, so a team confirms what is already configured without a dashboard login.
Seqera
Lists pipelines, workflow runs, and compute environments, submits Wave container builds, and returns build status and logs.
Wolfram alpha api
Returns short, spoken or LLM-formatted computed answers, checks how a query parses, and recovers pods from a timed-out computation.
Ready to connect Databox?
Authorize the account and your agent has all 7 actions from the first conversation.