Integration
Connect BigML and Streak
When New project fires in BigML, your agent runs Create Task in Streak, or New Box in Streak to Get Resource Status in BigML. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want BigML and Streak to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.
Set it up in your client
Claude Code
Run this in the directory you want to work in.
claude mcp add --transport http -s project apiant-ai https://mcp.apiant.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)Claude, web and desktop
Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.
Setup guide (opens in a new tab)Cursor
Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.
Setup guide (opens in a new tab)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)Codex and the ChatGPT desktop app
Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.
Setup guide (opens in a new tab)Any other MCP client
Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.
Setup guide (opens in a new tab)BigML holds the projects, datasets and models your data team works with, while Streak holds the pipelines, boxes and tasks the rest of the company lives in. Connecting them means a new BigML project can open a box in Streak with the right task on it, and Streak activity can pull the current state of a BigML resource back to the people tracking the work.
Example flows
What BigML and Streak can do together
From BigML to Streak
When New project in BigML
then Create Task in Streak
From Streak to BigML
Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.
Everything your agent can do with BigML and Streak
Triggers and actions 13 triggers · 25 actions
- New project
Triggered when a new project is created in BigML. Polls the BigML projects list endpoint and emits each project, deduplicated by its resource id.
- Get Resource Status
Retrieve a BigML resource by id (source/dataset/model/prediction) to poll its status and read results.
- List Datasets
List BigML datasets, optionally filtered/paginated.
- List Models
List BigML models, optionally filtered/paginated.
- List Sources
List BigML sources, optionally filtered/paginated.
- New Box
Triggered when a new box is added to the specified pipeline.
- New email thread
Triggered when a new email thread is added to the specified box.
- New event
Triggered when a new event occurs within any pipeline.
- New event in box
Triggered when a new event occurs within the specified box.
- New event in pipeline
Triggered when a new event occurs within the specified pipeline.
- New file
Triggered when a new file is added to the specified box.
- New Pipeline
Triggered when a new pipeline is added.
- New snippet
Triggered when a new snippet is added.
- New Stage
Triggered when a new stage is added to the specified pipeline.
- New Task in Box
Triggered when a new task is added to the specified box.
- New task in pipeline
Fires for each new task created in the selected Streak pipeline. Polls every box in the pipeline and emits each task once, identified by its task key.
- Task complete
Fires for each task marked complete in the selected Streak pipeline. Polls every box in the pipeline, keeps the tasks whose status is DONE, and emits each one once, identified by its task key.
- Create Box
Adds a new box to the specified pipeline.
- Create Comment
Adds a new comment to the specified box.
- Create Pipeline
Creates a new pipeline.
- Create Stage
Adds a new stage to the specified pipeline.
- Create Task
Adds a new task to the specified box.
- Delete Box
Deletes a box by its key.
- Delete Stage
Deletes a stage from the specified pipeline.
- Delete Task
Deletes a task by its key.
- Get Box
Gets a single box by its key.
- Get Current User
Returns the user associated with the API key.
- Get Pipeline
Gets a single pipeline by its key.
- List Boxes in Pipeline
Lists all boxes in the specified pipeline.
- List Fields
Lists all fields in the specified pipeline.
- List Pipelines
Lists all pipelines the user has access to.
- List Stages
Lists all stages in the specified pipeline.
- List Tasks in Box
Lists all tasks in the specified box.
- Move Box to Stage
Moves a box to a stage in the specified pipeline.
- Search
Searches boxes, contacts, and organizations across Streak.
- Update Box
Updates a box's name, notes, or stage.
- Update Box Field Value
Sets the value of a custom field on a box.
- Update Task
Updates a task's text, due date, or completion status.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from BigML
BigML to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
BigML to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
BigML to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
BigML to MailchimpMailchimp marketing automation and email platform.
BigML to ShopifyShopify is a commerce platform for online stores and retail point-of-sale.
BigML to QuickBooks OnlineQuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...
More into Streak
Gmail to StreakGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Questions
BigML and Streak, answered
Can a new BigML project open its own workspace in Streak?
Yes. The New project trigger in BigML can create a pipeline, a box or a stage in Streak, and you can add a task to that box in the same run. The agent tests every scenario, including a project that arrives with no datasets attached yet.
Can Streak show whether a BigML model or prediction is ready?
Streak triggers such as New Box or Task complete can run Get Resource Status in BigML to read the current state of a source, dataset, model or prediction. You can also run List Models, List Datasets or List Sources to pull what exists for a project.
What can start an automation from BigML?
Any of BigML's 1 trigger in the catalog, including New project. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Streak when something happens in BigML?
Any of Streak's 21 actions, including Create Pipeline, Create Stage, Create Box and Create Comment. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Streak to BigML?
Yes. When something happens in Streak, your agent can act in BigML too. This page covers both directions: Streak's triggers and BigML's actions are listed here as well.
Do I have to build a connector for BigML or Streak?
No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.
Can my AI client use BigML and Streak without building an automation?
Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.
What happens when something fails?
Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.
Is there a free plan?
Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.