How do I get a Pipefy API token and where do I find it?

Log in to Pipefy, click on your **Profile icon** (top-right), go to **Profile > API Access**, and generate a new token. Alternatively, use **Service Accounts** for team-based access. Copy the token immediately — it starts with `eyJhbG...`. Paste it into the API token field below. This token authenticates all GraphQL API requests to `https://api.pipefy.com/graphql`.

How do I move a card from one phase to another in a pipe?

Use the `move_card_to_phase` tool with the card_id (from list_cards or get_card) and the target phase_id (from get_pipe or list_phases). This advances the card through your workflow. For example, moving a card from 'New Requests' to 'In Review' phase. The card retains all its field values after moving. This is the primary way to progress items through your process.

Can I search for cards by a specific field value like email or customer name?

Yes! Use the `search_cards_by_field` tool with the pipe_id, field_id (the specific field to search in), and search_value (the text to find). This searches all cards in the pipe where that field contains your search text. It's perfect for finding cards by customer email, name, order number, or any custom field. Results include full card details with all field values.

How do I create a new card with custom field values?

Use the `create_card` tool with the pipe_id and a JSON object containing field values. The fields parameter should be a JSON object where keys are field IDs (from get_pipe) and values are the data to store. Example: `{ "name": "John Doe", "email": "john@example.com", "priority": "High" }`. You can also optionally specify a phase_id to start the card in a specific phase instead of the default first phase.

Pipefy MCP Server for Mastra AI 14 tools — connect in under 2 minutes

Name: Pipefy
Availability: InStock
Author: Vinkius

docs.mastra.ai/docs/agents/mcp-tools

Built by Vinkius GDPR 14 Tools SDK

Mastra AI is a TypeScript-native agent framework built for modern web stacks. Connect Pipefy through the Vinkius and Mastra agents discover all tools automatically — type-safe, streaming-ready, and deployable anywhere Node.js runs.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

typescript

import { Agent } from "@mastra/core/agent";
import { createMCPClient } from "@mastra/mcp";
import { openai } from "@ai-sdk/openai";

async function main() {
  // Your Vinkius token — get it at cloud.vinkius.com
  const mcpClient = await createMCPClient({
    servers: {
      "pipefy": {
        url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
      },
    },
  });

  const tools = await mcpClient.getTools();
  const agent = new Agent({
    name: "Pipefy Agent",
    instructions:
      "You help users interact with Pipefy " +
      "using 14 tools.",
    model: openai("gpt-4o"),
    tools,
  });

  const result = await agent.generate(
    "What can I do with Pipefy?"
  );
  console.log(result.text);
}

main();

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Pipefy MCP Server

Connect your Pipefy account to any AI agent and take full control of your process management workflows through natural conversation.

Mastra's agent abstraction provides a clean separation between LLM logic and Pipefy tool infrastructure. Connect 14 tools through the Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution — deployable to any Node.js host in one command.

What you can do

Pipe Discovery — List all pipes (processes) in your organization and inspect their structure, phases, and fields
Card Management — Create, read, update, and delete cards (items/records) flowing through your pipes
Field Updates — Update specific field values on existing cards as information changes or processes evolve
Phase Transitions — Move cards between phases to advance workflow steps (e.g., New → In Progress → Done)
Card Search — Search for cards by field value to find specific items by email, name, ID, or custom data
Card Cloning — Duplicate existing cards to quickly create similar items with pre-filled field values
Organization Info — View organization details, members, and available pipes
User Profile — Check your authenticated user profile and organization memberships

The Pipefy MCP Server exposes 14 tools through the Vinkius. Connect it to Mastra AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Pipefy to Mastra AI via MCP

Follow these steps to integrate the Pipefy MCP Server with Mastra AI.

Install dependencies

Run npm install @mastra/core @mastra/mcp @ai-sdk/openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.ts and run with npx tsx agent.ts

Explore tools

Mastra discovers 14 tools from Pipefy via MCP

Why Use Mastra AI with the Pipefy MCP Server

Mastra AI provides unique advantages when paired with Pipefy through the Model Context Protocol.

Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure — add Pipefy without touching business code

Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation

TypeScript-native: full type inference for every Pipefy tool response with IDE autocomplete and compile-time checks

One-command deployment to any Node.js host — Vercel, Railway, Fly.io, or your own infrastructure

Pipefy + Mastra AI Use Cases

Practical scenarios where Mastra AI combined with the Pipefy MCP Server delivers measurable value.

Automated workflows: build multi-step agents that query Pipefy, process results, and trigger downstream actions in a typed pipeline

SaaS integrations: embed Pipefy as a first-class tool in your product's AI features with Mastra's clean agent API

Background jobs: schedule Mastra agents to query Pipefy on a cron and store results in your database automatically

Multi-agent systems: create specialist agents that collaborate using Pipefy tools alongside other MCP servers

Pipefy MCP Tools for Mastra AI (14)

These 14 tools become available when you connect Pipefy to Mastra AI via MCP:

clone_card

You must provide the card_id of the card to clone. The new card is created in the same pipe as the original, starting at the first phase. This is useful for creating similar requests, repeating processes, or using an existing card as a template for new items. The cloned card gets a new unique ID but retains all field data. Clone an existing card to create a duplicate

create_card

You must provide the pipe_id and a JSON object containing field values matching the pipe's required fields. Fields are key-value pairs where keys are field IDs and values are the data to store. Optionally specify a phase_id to start the card in a specific phase (defaults to first phase). Example fields: { "name": "John Doe", "email": "john@example.com", "priority": "High" } Create a new card in a Pipefy pipe

delete_card

You must provide the card_id. This action cannot be undone. Use this to remove test cards, duplicates, or items that were created in error. Be careful as this will also remove all associated data including comments, attachments, and field values for that card. Delete a card from a pipe

get_card

Use the card_id obtained from list_cards to inspect full card information. This is useful for reviewing card details before updating fields or moving to another phase. Get detailed information about a specific card

get_organization

Use the organization_id to inspect your organization's structure, understand team membership, and discover available pipes for card management. Get details of a Pipefy organization

get_phase

Phases represent steps in a pipe's workflow. Use the phase_id obtained from get_pipe or list_phases to inspect phase configuration. This helps understand what fields are required at each step of the workflow. Get details of a specific phase

get_pipe

Each pipe represents a workflow or process with multiple phases (steps) and custom fields. Use the pipe_id to get the structure of a pipe before creating cards or managing cards within it. The response includes all phases with their IDs, names, and the custom fields defined for the pipe. Get details of a specific Pipefy pipe (process)

get_user_profile

Use this to verify API token access and discover organization IDs needed for other queries. This is also useful for understanding which organizations and pipes the user has access to. Get the authenticated user profile

list_cards

Cards represent individual items flowing through the pipe's workflow phases (e.g., requests, tasks, tickets, leads). You must provide the pipe_id. Optionally filter by phase_id to see cards in a specific phase. Each card includes title, current phase, completion status, due date, and assignees. Use this to monitor workflow progress and identify cards that need attention. List all cards in a pipe with optional phase filter

list_phases

Each phase represents a stage that cards flow through in the process. Use this to understand the workflow structure and identify phase IDs for filtering cards or moving cards between phases. The response includes phase names and card counts. List all phases in a pipe

list_pipes

Each pipe represents a structured workflow with phases, fields, and cards. You must provide the organization_id which can be found in your Pipefy URL or obtained from get_user_profile. Use this to discover all available pipes before managing cards within them. List all pipes in an organization

move_card_to_phase

You must provide the card_id and the target phase_id. This is the primary way to advance workflow items through the pipe's process steps. Common use cases: moving a request from "New" to "In Review", advancing a lead to "Qualified", or progressing a task to "Completed". The card retains all its field values after moving. Move a card to a different phase in the pipe

search_cards_by_field

This is useful for finding cards by email, name, ID, or any custom field content. You must provide the pipe_id, field_id (the field to search in), and search_value (text to find). Results include card title, current phase, status, and all field values for matching cards. The search uses a "contains" operator for flexible matching. Search cards in a pipe by a specific field value

update_card_field

You must provide the card_id, the field_id of the field to update, and the new value as a string. This is useful for updating card information as requests progress or details change. Common updates: changing priority, updating contact info, modifying descriptions, or setting dates. Update a specific field value on a card

Example Prompts for Pipefy in Mastra AI

Ready-to-use prompts you can give your Mastra AI agent to start working with Pipefy immediately.

"List all pipes in my organization and show me the cards in the 'IT Support' pipe."

"Create a new purchase request card in the Purchase Requests pipe with these details: Requester: Maria Silva, Item: MacBook Pro 16", Quantity: 2, Justification: Design team replacement."

"Search for all cards in the IT Support pipe where the email field contains 'john@company.com' and show me their current status."