Build solutions, not workarounds.
What do you want Pneumatic and Yutori 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 Pneumatic can start in Yutori
When Task Completed in Pneumatic
then Run Browsing Task in Yutori
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 Pneumatic and Yutori
Triggers and actions 4 triggers · 21 actions
- Task Completed
Triggers when some task is completed.
- Task Returned
Triggers when a process is returned to this task.
- Workflow Completed
Triggers when a workflow is completed.
- Workflow Started
Triggers when a new workflow is started.
- Get Task
Get a single task by id.
- Get Template
Get a specific workflow template by id.
- List Templates
List all workflow templates in the account.
- List Users
List users in the account.
- Run Workflow
Run a New Workflow
- Update Task
Complete a task.
- Add Scout
Creates a new scout to continuously monitor the web on a schedule for a natural-language query.
- Delete Scout
Permanently deletes a scout.
- Get Browsing Task Result
Get the current status of a Yutori browsing task and its results once it has completed.
- Get Browsing Task trajectory
Gets the step-by-step trajectory (screenshots) of a completed browsing task.
- Get Research Task Result
Fetches the current status and result of a research task.
- Get Scout
Retrieves a single scout by id.
- List Browsing Tasks
Lists browsing tasks for the account, optionally filtered by status.
- List Research Tasks
Lists the research tasks in the Yutori account, optionally filtered by status.
- List Scout updates
Lists the updates a Yutori scout has reported, newest first.
- Mark scout as done
Marks a scout as complete, ending its monitoring schedule.
- Restart Scout
Restarts a scout that was previously marked as done, so it resumes monitoring.
- Run Browsing Task
Launches a Yutori browsing agent on a cloud (or local) browser to carry out a natural-language task starting from a URL. Returns the task id immediately; the task runs asynchronously.
- Run Research Task
Launches a one-time research task on the web and returns its task id and status. Fetch the finished results with Get Research Task Result.
- Update Scout
Updates selected settings of an existing Yutori scout. Only the fields you fill in are changed; everything else stays as it is.
- Update Scout email settings
Turns email notifications on or off for a scout and adds or removes email subscribers. Provide at least one of the optional fields.
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 Pneumatic
Pneumatic to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Pneumatic to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Pneumatic to StripeStripe is a payment processing platform for online businesses.
Pneumatic to ShopifyShopify is a commerce platform for online stores and retail point-of-sale.
Pneumatic to QuickBooks OnlineQuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...
Pneumatic to TrelloTrello is a visual collaboration tool that organizes projects into boards, lists, and cards.
More into Yutori
HubSpot to YutoriHubSpot is your all-in-one stop for all of your marketing software needs.
Google Sheets to YutoriGoogle Sheets
Gmail to YutoriGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to YutoriGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Questions
Pneumatic and Yutori, answered
What can start an automation from Pneumatic?
Any of Pneumatic's 4 triggers in the catalog, including Task Completed, Workflow Completed, Task Returned and Workflow Started. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Yutori when something happens in Pneumatic?
Any of Yutori's 15 actions, including Update Scout, Update Scout email settings, Add Scout and Get Browsing Task Result. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Yutori to Pneumatic?
Yutori has no triggers in the catalog today, so automations start in Pneumatic. If you need the other direction, ask: your agent reads Yutori's API documentation and adds it.
Do I have to build a connector for Pneumatic or Yutori?
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.