Build solutions, not workarounds.
What do you want Pipefy and Ngrok 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 Pipefy can start in Ngrok
When Moved Card in Pipefy
then Add API key in Ngrok
When New Card in Pipefy
then Add credential in Ngrok
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 Pipefy and Ngrok
Triggers and actions 6 triggers · 21 actions
Trigger
Done CardTriggers when a card is done.
Trigger
Moved CardTriggers when a card is moved.
Trigger
New CardTriggers when a new card is created.
Trigger
New Database RecordTriggers when a new record is created.
Trigger
Updated Card FieldTriggers when a card field is updated.
Trigger
Updated Record FieldTriggers when a record field is updated.
Action
Create CardCreates a card in a Pipefy pipe, filling in its start form fields.
Action
Create RecordCreates a new table record.
Action
Delete CardPermanently deletes a card from its pipe.
Action
Delete Database RecordDelete a database table record by ID via the GraphQL `deleteTableRecord(input: {id})` mutation.
Action
Find CardReturns the cards in a pipe whose chosen field matches the specified value.
Action
Find Database RecordsFind a database records by title.
Action
Get CardRetrieves a single Pipefy card by its id, including its phase, pipe, assignees, labels, attachments and field values.
Action
Get Database RecordFetch a single database table record by ID via the GraphQL `table_record(id: ID)` query.
Action
Move CardMoves a Pipefy card to another phase of its pipe.
Action
Update Card FieldSets a new value on one field of an existing Pipefy card.
Action
Update Database RecordUpdate a database table record's title/fields via the GraphQL `updateTableRecord(input: {id, title})` mutation.
Action
Add API key/api_keys
Action
Add credential/credentials - create a tunnel authtoken credential.
Action
Add IP policy/ip_policies
Action
Add IP policy rule/ip_policy_rules
Action
Get IP policy ruleFetches an IP policy rule by ID, including its CIDR range, allow/deny action and the IP policy it belongs to. An error occurs if the rule is not found.
Action
Get reserved domain/reserved_domains/{id}
Action
List API keys/api_keys
Action
List credentials/credentials
Action
List IP policies/ip_policies
Action
List reserved domains/reserved_domains (paginated with before_id/limit).
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 Pipefy
Pipefy to TrelloTrello is a visual collaboration tool that organizes projects into boards, lists, and cards.
Pipefy to Spaceflight NewsSpaceflight News API aggregates news coverage of spaceflight and the space industry from many publishers.
Pipefy to SparrowDeskSparrowDesk is an AI-first helpdesk that unifies customer support across email & chat while automating...
Pipefy to TimingTiming is an automatic time tracking app for macOS.
Pipefy to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Pipefy to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
More into Ngrok
HubSpot to NgrokHubSpot is your all-in-one stop for all of your marketing software needs.
Salesforce to NgrokSalesforce is a leading enterprise customer relationship management (CRM) platform.
Slack to NgrokSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Google Sheets to NgrokGoogle Sheets
Gmail to NgrokGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to NgrokGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Questions
Pipefy and Ngrok, answered
What can start an automation from Pipefy?
Any of Pipefy's 6 triggers in the catalog, including Moved Card, New Card, New Database Record and Updated Card Field. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Ngrok when something happens in Pipefy?
Any of Ngrok's 10 actions, including Add API key, Add credential, Add IP policy and Add IP policy rule. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Ngrok to Pipefy?
Ngrok has no triggers in the catalog today, so automations start in Pipefy. If you need the other direction, ask: your agent reads Ngrok's API documentation and adds it.
Do I have to build a connector for Pipefy or Ngrok?
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.