Integration
Connect OKrunit to PredictHQ
When something happens in OKrunit, your agent does the next thing in PredictHQ. Describe it 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 OKrunit and PredictHQ to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiAny 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)Example flows
What OKrunit can start in PredictHQ
When New Approval Request in OKrunit
then Add saved location in PredictHQ
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 OKrunit and PredictHQ
Triggers and actions 2 triggers · 15 actions
- Approval Decided
Triggers when an approval request is approved or rejected.
- New Approval Request
Triggers when a new approval request is created in your organization.
- Add Comment
Add a comment to an existing approval request.
- Find Approval Request
Find a specific approval request by its ID.
- Find Approvals
Search for approval requests with filters.
- Request Approval
Create an approval request for a person to approve or reject. The request is created immediately and starts out pending; watch the Approval Decided trigger for the outcome.
- Add saved location
Create a reusable business location for consistent querying across Events, Features, Beam, and Forecasts APIs.
- Delete saved location
Delete a saved location by id.
- Find broadcasts
Search broadcast (TV/sports schedule) records by filters such as location, date range, and category.
- Find events by criteria
Search for real-world events by location, date range, category, rank, and other filters.
- Find places by criteria
Search PredictHQ's places gazetteer by name/region/country.
- Find saved locations by criteria
Search existing saved locations.
- Get ML features
Fetch pre-built, model-ready demand features aggregated from real-world events for a location and date range.
- Get predicted impact area
Return the predicted geographic impact area for a Beam analysis.
- Get saved location
Fetch a single saved location by id.
- Get suggested radius
Return the suggested search radius for a given location, used to size Beam/event queries.
- Update saved location
Update an existing saved location's definition.
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 OKrunit
OKrunit to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
OKrunit to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
OKrunit to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
OKrunit to StripeStripe is a payment processing platform for online businesses.
OKrunit to ShopifyShopify is a commerce platform for online stores and retail point-of-sale.
OKrunit to QuickBooks OnlineQuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...
More into PredictHQ
Frihet to PredictHQFrihet is a Spanish business-management and accounting platform for small companies and freelancers.
Google Sheets to PredictHQGoogle Sheets
Gmail to PredictHQGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Questions
OKrunit and PredictHQ, answered
What can start an automation from OKrunit?
Any of OKrunit's 2 triggers in the catalog, including New Approval Request and Approval Decided. Describe the moment in plain language and your agent picks the right one.
What can your agent do in PredictHQ when something happens in OKrunit?
Any of PredictHQ's 11 actions, including Update saved location, Add saved location, Find broadcasts and Find events by criteria. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from PredictHQ to OKrunit?
PredictHQ has no triggers in the catalog today, so automations start in OKrunit. If you need the other direction, ask: your agent reads PredictHQ's API documentation and adds it.
Do I have to build a connector for OKrunit or PredictHQ?
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.
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.