Integration
Connect Wachete to Extracta.ai
When New notification for monitor fires in Wachete, your agent runs Add classification in Extracta.ai. 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 Wachete and Extracta.ai 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)Example flows
What Wachete can start in Extracta.ai
When New notification for monitor in Wachete
then Add classification in Extracta.ai
When Any new notification in Wachete
then Add extraction in Extracta.ai
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 Wachete and Extracta.ai
Triggers and actions 2 triggers · 17 actions
Trigger
Any new notificationFires when there is a new change notification from any monitor in your Wachete account.
Trigger
New notification for monitorFires when there is a new change notification from the specified Wachete monitor (taskId).
Action
Create monitorCreate a new Wachete monitor (wachet) that watches a web page or part of a page for changes.
Action
Delete monitorDelete a Wachete monitor by its ID.
Action
Get monitorGet information about a specific Wachete monitor by its ID.
Action
Get monitor dataGet the captured data/history for a Wachete monitor, optionally as a diff and within a date range.
Action
List foldersList folder contents, optionally under a parent folder.
Action
List notificationsList change notifications, optionally filtered by monitor (taskId) and date range.
Action
Update monitorChange the settings of an existing Wachete monitor — name, URL, watched/excluded XPath, regex, note, job type, check frequency and location, crawl options, folder, alerts, notification endpoints, headers and proxies. A partial update: the op first reads the monitor's current record, overlays only the fields you filled in, then writes the merged record back, so anything you leave blank keeps its current value — including settings this op does not expose. Identify the monitor by its id. Check frequency is in seconds (86400 = daily) and is ignored if not positive; the true/false options take the words true or false; alerts, notification endpoints, headers and proxies take JSON. Returns the monitor id, name and URL after the update plus the full monitor record.
Action
Add classificationCreates a document classification with a list of document types that uploaded documents can be classified into. Returns the new classification's id.
Action
Add extractionCreates a new data extraction in Extracta.ai that defines which fields to pull out of uploaded documents. Returns the new extraction's id, which you use when uploading files for processing.
Action
Delete classificationPermanently deletes a document classification, including all of its batches, results and uploaded files.
Action
Delete extractionPermanently deletes an extraction with all its batches and files, or just one batch or one file within it.
Action
Get classificationReturns the details of a document classification, including its name, description and configured document types with their keywords and linked extraction templates.
Action
Get creditsReturns the number of credits currently available on your Extracta.ai account, where one credit processes one page.
Action
Get extractionReturns the setup of an extraction: its name, description, language, options, the fields it extracts, and the batches processed under it.
Action
Get extraction resultsReturns the extracted data for a batch of documents processed by an extraction, or its waiting status if processing is not finished. Optionally narrows the results to a single file.
Action
Update classificationUpdates an existing document classification's name, description and document types.
Action
Update extractionUpdates an existing Extracta extraction's name, description, language, processing options or fields to extract. Anything left blank stays unchanged.
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 Wachete
Wachete to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Wachete to ActiveCampaignActiveCampaign is a marketing automation, email marketing, and CRM platform.
Wachete to JIRAAtlassian JIRA Cloud — issue tracking and project management.
Wachete to ZoomZoom unifies cloud video conferencing, simple online meetings, group messaging, and a software-based...
Wachete to WebflowWebflow is a professional website builder and CMS for designing, building, and launching responsive...
Wachete to AnthropicAnthropic builds Claude, a family of large language models.
More into Extracta.ai
HubSpot to Extracta.aiHubSpot is your all-in-one stop for all of your marketing software needs.
Salesforce to Extracta.aiSalesforce is a leading enterprise customer relationship management (CRM) platform.
Slack to Extracta.aiSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Google Sheets to Extracta.aiGoogle Sheets
Gmail to Extracta.aiGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to Extracta.aiGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Questions
Wachete and Extracta.ai, answered
What can start an automation from Wachete?
Any of Wachete's 2 triggers in the catalog, including New notification for monitor and Any new notification. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Extracta.ai when something happens in Wachete?
Any of Extracta.ai's 10 actions, including Update classification, Update extraction, Add classification and Add extraction. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Extracta.ai to Wachete?
Extracta.ai has no triggers in the catalog today, so automations start in Wachete. If you need the other direction, ask: your agent reads Extracta.ai's API documentation and adds it.
Do I have to build a connector for Wachete or Extracta.ai?
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 Wachete and Extracta.ai 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.