Pipefy MCP. Manage entire workflows without leaving your chat.
Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Pipefy manages your operational workflows by exposing every core process action—from listing pipes to updating field values on specific cards.
Your AI client can create new records, move items between phases, and search for tasks using natural language commands. It’s full-stack workflow control without opening the Pipefy dashboard.
What your AI agents can do
Clone card
Duplicates an existing card in a pipe, creating a template for similar requests while keeping all original field data.
Create card
Creates a new record (card) in a specified Pipefy pipe using key-value pairs for required field data.
Delete card
Permanently removes a card and all its associated data, comments, and attachments from the pipe.
Retrieves organizational details, listing all available pipes and team memberships.
Moves a specific card from one defined phase to another in the workflow process.
Builds and submits a new card (item) into any specified pipe, populating required fields with data provided by the user.
Searches all cards within a pipe using custom field criteria like email or name to locate specific records.
Updates one or more data fields on an existing card, such as changing status, priority, or notes.
Ask AI about this MCP
Supported MCP Clients
Waiting for input…
Pipefy MCP Server: 14 Tools for Workflow Management
Use these tools to read organization structure, list all pipes, search specific records, and execute core workflow actions like creating or advancing cards.
019d75f5clone card
Duplicates an existing card in a pipe, creating a template for similar requests while keeping all original field data.
019d75f5create card
Creates a new record (card) in a specified Pipefy pipe using key-value pairs for required field data.
019d75f5delete card
Permanently removes a card and all its associated data, comments, and attachments from the pipe.
019d75f5get card
Retrieves all detailed information about one specific card using its unique ID for review before making changes.
019d75f5get organization
Fetches the structure of your organization, including team membership and available processes.
019d75f5get phase
Gets configuration details for a single phase within a pipe's workflow to understand its requirements.
019d75f5get pipe
Retrieves the full structure of any specific Pipefy process, including all phases and custom fields it uses.
019d75f5get user profile
Confirms your authenticated user details and lists which organizations you have access to within Pipefy.
019d75f5list cards
Lists all cards in a pipe, optionally filtering by phase or other criteria, to monitor overall workflow progress.
019d75f5list phases
Retrieves the names and counts of phases within a specific pipe to map out its complete process flow.
019d75f5list pipes
Shows every available workflow (pipe) across your entire organization's account.
019d75f5move card to phase
Advances a card by moving it from its current phase to a target phase, progressing the workflow step.
019d75f5search cards by field
Finds cards in a pipe using flexible search criteria against custom fields like email or name.
019d75f5update card field
Changes the value of one specific field on an existing card, useful for updating status or priority.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Pipefy, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
This Pipefy MCP Server gives your AI client full control over your operational workflows, letting you manage every core process action without opening a single dashboard. You'll use it to handle everything from listing entire processes to updating field values on specific cards.
Discovering Your Pipes and Structure
You can start by checking out the whole picture. The server lets you list_pipes, showing every workflow (or 'pipe') your organization runs. You'll also get a rundown of everything about your account using get_user_profile, confirming who you are and which organizations you have access to. If you need to map out what any specific process does, call get_pipe; this returns the full structure for that pipe, including all custom fields it uses and every phase it moves through.
To understand a single step in time, use get_phase, which provides configuration details for one phase within a workflow. You can also check out your team's setup by running get_organization, which gives you the full structure of your organization, including who's on which team.
Monitoring and Finding Tasks
You don't have to guess where a card is. Use list_pipes and then run list_phases against a specific pipe to map out all the names and counts of phases, showing you the complete process flow step by step. To see what's actively moving through any given workflow, use list_cards.
This function lists every card in a pipe; you can narrow down that list by phase or other criteria so you only monitor the progress you care about.
Need to find one specific record? You don't have time to scroll. Use search_cards_by_field to locate cards within a pipe using flexible search rules against custom fields, like an email address or a name. If you know the unique ID of a card and need all the details before making any changes—like checking notes or attachments—use get_card.
This pulls every piece of information about that single record.
Building and Manipulating Records
Want to start something new? You use create_card to build and submit a brand-new card into any pipe. You just feed it the required field data, and it gets submitted right away. If you need to replicate a request or template, use clone_card, which duplicates an existing card in a pipe, keeping all the original field data intact for your new record.
When you're done with a task, delete_card permanently removes that card and everything attached to it—comments, files, the whole nine yards.
Moving Data and Updating Details
Once you’ve created or found a card, you gotta move it through the process. Use move_card_to_phase to advance a card by moving it from its current phase straight into a target phase, pushing the workflow forward. If something changes on an existing card—say, the status needs updating, or the priority shifts—use update_card_field.
This lets you change the value of one specific field on any active card without having to open up the full record. You've got total control over your operational workflows with these tools.
How Pipefy MCP Works
- 1 Subscribe to the server and provide your Pipefy API token.
- 2 Your AI client first calls
list_pipesusing your organization ID to determine which workflows exist. - 3 You then tell the agent what needs doing (e.g., 'Move card X to In Progress'). The agent uses
move_card_to_phaseand reports success or failure.
The bottom line is: Your AI client handles all API calls, letting you manage complex workflows through simple chat prompts.
Who Is Pipefy MCP For?
Ops engineers who are tired of clicking through dashboards just to update a single field. Project Managers running multiple overlapping processes across different teams. Support staff needing to find and modify customer records fast. Anyone whose job involves moving data items through structured, multi-step workflows.
Uses list_pipes to map out department processes and uses create_card to initiate new requests for hardware or software.
Monitors multiple pipes by calling list_cards and identifies bottlenecks that need manual intervention or field updates via update_card_field.
Uses search_cards_by_field with a customer's email address to instantly pull up their ticket history, then uses move_card_to_phase to change its status from 'New' to 'Resolved'.
What Changes When You Connect
- Stop clicking through dashboards. You can update a card's priority or change its owner using
update_card_field—all in one conversation turn. - Never get lost in process steps again. Use
list_pipesto see every workflow your company runs and understand exactly how each item moves from start to finish. - Need to check a record's status? Instead of manually searching, run
search_cards_by_fieldby email or ID to pull up the exact card details instantly. - Don't repeat work. Use
clone_cardto duplicate an existing request and populate all necessary fields for a new item in seconds. - Advance tickets faster. You can move cards between phases using
move_card_to_phase, automating the step-by-step progress of any project.
Real-World Use Cases
The HR Onboarding Flow
An Operations Analyst needs to see all open onboarding tasks for a new hire. They ask their agent to 'List cards in the HR Onboarding pipe'. The agent calls list_cards and reports back that 4 out of 7 required steps are still pending, allowing the analyst to focus only on the bottlenecks.
The Support Ticket Update
A Support Specialist gets a follow-up email with new details for ticket #123. Instead of logging into Pipefy, they tell their agent: 'Update card 123's description and set its priority to High'. The agent runs update_card_field instantly.
The Project Kickoff
A Project Manager is starting a new project and needs a template. They ask the agent to 'Clone card 500 in the Project Request pipe'. The agent executes clone_card, creating an exact duplicate with a unique ID, saving hours of manual data entry.
Finding Lost Records
A team member needs to find all purchase requests from 'Jane Doe' that were submitted last week. They use the agent to search_cards_by_field by name, and the system returns a list of matching card IDs and their current status.
The Tradeoffs
Trying to fetch data for every possible field.
Asking the agent, 'Give me all the details about this card: name, email, priority, date, attachments...' This is too vague and inefficient because fields vary by pipe.
→
Be specific. Use get_card with a single Card ID (e.g., 'Get card 12345') or use search_cards_by_field to narrow down the scope first.
Manually guessing phase IDs.
Telling the agent, 'Move it to Phase 7.' The system won't know what that means if you don't know the internal pipe structure.
→
First run list_phases for the relevant pipe. Then use the human-readable phase name when calling move_card_to_phase.
Doing a full database dump of all cards.
Asking, 'List every single card in the entire organization.' This is too broad and risks hitting rate limits or returning irrelevant data.
→
Always specify the pipe ID first. Start by running list_pipes to find the right workflow, then use list_cards on that specific pipe.
When It Fits, When It Doesn't
Use this server if your primary pain point is managing structured, multi-step workflows (like ticket processing or approval chains). If you need to move data from a list of emails into a spreadsheet, this isn't the tool—use a database connector. But if that data needs to follow defined steps and change status in a system like Pipefy, this is perfect. Use list_pipes first to scope your work; then use search_cards_by_field to find the starting point, followed by move_card_to_phase to advance it.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Pipefy. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 14 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Updating a single field in Pipefy usually means 5-7 clicks and navigating multiple tabs.
Right now, if an item's priority changes or the contact details get updated, you have to open the card, find the right section (is it 'Status'? Is it 'Details'?), manually change the field, and hit save. This is slow and prone to error.
With this MCP server, your AI client handles that whole process. You just tell it: 'Update card 12345's priority to High.' Done. It runs `update_card_field` for you—no dashboard navigation required.
The Pipefy MCP Server gets your workflow running instantly.
You don't have to remember which phase ID corresponds to 'Awaiting Manager Review,' or what the specific field IDs are for 'Requester Name.' The agent handles all that messy backend logic.
This means you focus on the process—the business outcome—not the mechanics of the software. It’s simple, direct control over your entire workflow.
Common Questions About Pipefy MCP
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.
How do I use the `list_pipes` tool to see every process in my organization? +
You need to provide your organization ID when running list_pipes. This action returns a list of all available pipes, letting you map out which workflows exist before managing any cards within them.
Before I use the `create_card` tool, how do I verify required fields using `get_pipe`? +
Run get_pipe with a specific pipe ID. The response details all phases and lists every custom field required for that workflow. This lets you build accurate data payloads for card creation.
What happens if I use the `delete_card` tool with an existing card? +
The card is permanently removed, and this action cannot be undone. It deletes all associated data—including comments, attachments, and field values—so proceed only when you are certain it's unnecessary.
How does the `clone_card` tool help me repeat a process or create templates? +
It duplicates an existing card using just its ID. This retains all original field values and history, giving you a new unique item perfect for templating recurring requests without manual data entry.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Good Grants
Discover and manage grant applications with a platform that matches your organization to the right funding opportunities.
Height (Project Management)
Manage projects and tasks via Height — track activities, list tasks, and manage workspace lists.
Procore
Manage construction projects via Procore — track RFIs, submittals, punch lists, daily logs, and drawings from any AI agent.
You might also like
NetBird
Automate Zero Trust networking via NetBird — manage accounts, users, and access controls directly from any AI agent.
Artsy
Global art database — search artists, artworks, and shows via AI.
R2R
Equip your AI with direct access to your R2R engine — execute vector searches, run precise RAG queries, and manage your documents.