Pipefy Connector for AI agents.
14 live capabilities
Manage your organization's workflow automation and task tracking through natural conversation.
Waiting for input…
Why people use Pipefy
Pipefy Workflow Automation for Faster Task Tracking
With this Connector, you just tell your agent what to do. You can ask it to find every card for a specific customer and move them to the next phase in one go. You get a way to keep your project moving without the manual overhead of navigating a complex dashboard.
What Vinkius changes
You stop clicking through dashboards and start managing your workflows with plain text.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Support Triage
A support lead asks the agent to find all cards with a specific email and move them to the 'In Progress' phase.
- Real-world use case 02
Purchase Requests
A manager tells the agent to clone a 'Software Request' card and fill in the new user's details and justification.
- Real-world use case 03
Project Tracking
An ops person asks the agent to list all cards in the 'Design' pipe that are currently in the 'Review' phase.
Complete set · 14capabilities
The complete Pipefy capability set.
These are the exact actions your AI can choose when you ask it to work with Pipefy.
01—04
4 capabilities in this set.
Part of 14 available through Pipefy.
- 01 Capability
Clone card
Create a duplicate of an existing card in the same pipe. This is useful for using an existing card as a template for new items.
- 02 Capability
Create card
Add a new card to a specific Pipefy pipe with custom field values. This helps you log new requests without manual data entry.
- 03 Capability
Delete card
Permanently remove a card and all its associated data from a pipe. Use this to clean up test cards or errors.
- 04 Capability
Get card
Pull the full details of a specific card to review its data. This is helpful before you update fields or move it to a new phase.
05—08
4 capabilities in this set.
Part of 14 available through Pipefy.
- 05 Capability
Get organization
View the structure of your organization. It helps you understand team membership and discover available pipes.
- 06 Capability
Get phase
Inspect a specific phase to see what fields are required at that step. This helps you understand the workflow requirements.
- 07 Capability
Get pipe
Retrieve the structure of a specific pipe. It shows all phases, names, and custom fields defined for that process.
- 08 Capability
Get user profile
Check your authenticated profile to verify your API access. It also shows which organizations and pipes you can see.
09—11
3 capabilities in this set.
Part of 14 available through Pipefy.
- 09 Capability
List cards
See all cards in a pipe with an optional filter for a specific phase. Use this to monitor progress and find cards needing attention.
- 10 Capability
List phases
Get a list of all stages in a pipe. This helps you identify phase IDs for filtering cards or moving them through the workflow.
- 11 Capability
List pipes
Discover all available pipes within your organization. This is the first step to finding where your cards live.
12—14
3 capabilities in this set.
Part of 14 available through Pipefy.
- 12 Capability
Move card to phase
Move a card to a different step in the workflow. This is the primary way to advance items from one stage to the next.
- 13 Capability
Search cards by field
Find specific cards by searching for text within a field like email, name, or ID. It uses a contains operator for flexible matching.
- 14 Capability
Update card field
Change a specific piece of information on a card. This is useful for updating priority, contact info, or descriptions as requests evolve.
Set up in minutes
One URL. Then ask Pipefy to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Pipefy from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_0jLK89rkHO1lUYBbfrE97LkZ5Zz4CLCz35Qe76YH/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Pipefy, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Pipefy for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_0jLK89rkHO1lUYBbfrE97LkZ5Zz4CLCz35Qe76YH/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Pipefy URL.
- Step 03
Save and start
Save the connection and enable Pipefy in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"pipefy": {
"url": "https://edge.vinkius.com/vk_preview_0jLK89rkHO1lUYBbfrE97LkZ5Zz4CLCz35Qe76YH/mcp"
}
}
} - Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Pipefy
Open Agent mode in chat and ask: "Using Pipefy, help me...". 14 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"pipefy": {
"url": "https://edge.vinkius.com/vk_preview_0jLK89rkHO1lUYBbfrE97LkZ5Zz4CLCz35Qe76YH/mcp"
}
}
} - Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Pipefy
Ask Copilot: "Using Pipefy, help me...". 14 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"pipefy": {
"url": "https://edge.vinkius.com/vk_preview_0jLK89rkHO1lUYBbfrE97LkZ5Zz4CLCz35Qe76YH/mcp"
}
}
} - Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Pipefy
Open Cascade and ask: "Using Pipefy, help me...". 14 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"pipefy": {
"url": "https://edge.vinkius.com/vk_preview_0jLK89rkHO1lUYBbfrE97LkZ5Zz4CLCz35Qe76YH/mcp"
}
}
} - Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Pipefy
Ask Cline: "Using Pipefy, help me...". 14 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add pipefy --transport http "https://edge.vinkius.com/vk_preview_0jLK89rkHO1lUYBbfrE97LkZ5Zz4CLCz35Qe76YH/mcp" - Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Pipefy
Ask Claude: "Using Pipefy, show me...". 14 tools are ready
Where the request belongs
Work Pipefy can move forward.
This is for the operations lead who is drowning in manual updates and the support manager who is tired of hunting for specific tickets in a messy pipe.
Operations Manager
Moves cards through complex approval chains and updates status fields without manual entry.
Support Lead
Searches for customer emails to quickly find and update related requests in a high-volume pipe.
Project Coordinator
Clones recurring tasks and manages field values as new projects move through the workflow.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsFlow
Manage projects, tasks, and team collaboration via AI agents with Flow (getflow.com).
Zeev
Digitize business processes with BPMN workflows, electronic forms, and approval chains that replace paper and email chaos.
Kissflow
Build low-code workflows, process apps, and case management solutions that digitize operations without heavy IT involvement.
Pipedrive Products
Manage your product catalog and attach products to deals in Pipedrive.
HiFlow
Workflow and business process management.
CRM PipeRun
Manage your sales pipeline and activities via PipeRun. track tasks, upload files, and organize deals directly from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Pipefy connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Pipefy.
The practical details behind the request, access and result.
Can the Pipefy MCP help me manage my team's tasks?
Yes, it lets you manage cards, move them between phases, and update fields using natural language. This makes it much faster to keep your team's tasks moving without manually clicking through the dashboard.
How does the Pipefy MCP handle moving cards between different stages?
You can simply tell your agent which card to move and which phase it should go to. The Connector handles the transition automatically while keeping all your existing field data intact.
Can I use the Pipefy MCP to find specific requests by email?
Yes, you can search for cards using specific field values like email addresses. This is great for quickly locating customer requests in a high-volume pipe.
Does the Pipefy MCP support cloning cards for recurring work?
It does. You can ask your agent to clone an existing card to create a duplicate. This is a great way to use a card as a template for repeating processes.
Can I use the Pipefy MCP to update specific fields on a card?
Absolutely. You can tell your agent to change specific pieces of information, such as the priority level, status, or contact details on any card in your pipes.
How do I connect the Pipefy MCP to my AI client?
Once you subscribe, you just need to provide your Pipefy API token. Your AI client will then be able to see your pipes and perform actions on your behalf.
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 capability 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 capability 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 capability 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.
One connection away
Give your agent a direct line to Pipefy.
Connect Pipefy once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available