home / mcp / pipefy mcp server

Pipefy MCP Server

Provides access to Pipefy data sources and actions for pipes, cards, tables, and records through MCP-compatible endpoints.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "angeelvallem-pipefy-mcp": {
      "command": "pipefy-mcp",
      "args": [],
      "env": {
        "PIPEFY_API_TOKEN": "your_api_token_here"
      }
    }
  }
}

This MCP server enables you to connect Pipefy’s GraphQL endpoints with large language models, giving you practical tools to manage pipes, cards, database tables, and records directly through natural language interactions.

How to use

You interact with the Pipefy MCP server by launching it locally and connecting your MCP client. Use the available tools to list, inspect, create, and search pipes, cards, tables, and records. The server supports both human-readable Markdown outputs and machine-friendly JSON outputs, so your LLM can present results to users or feed structured data back into workflows.

How to install

Prerequisites: Python 3.8+ and pip must be available on your system. You can also run the server as a script via your system’s command line. The following steps show the supported installation and startup paths.

# Install dependencies using uv
uv sync

# Or install as a Python package in editable mode
pip install -e .

Configuration and running the server

Set your Pipefy API token as an environment variable before starting the server. This token authenticates requests to the Pipefy API.

export PIPEFY_API_TOKEN=your_api_token_here

Run the server with stdio transport

You can run the server in stdio mode either by calling the Python entry point or by using the script installed for easy access.

python main.py

# Or if you have the script installed as a CLI tool
pipefy-mcp

Cursor IDE integration

If you use the Cursor IDE, configure the MCP connection to point to the local Python entry point so the IDE can invoke the server directly.

{
  "mcpServers": {
    "pipefy": {
      "command": "python",
      "args": ["/path/to/pipefy-mcp/main.py"],
      "env": {
        "PIPEFY_API_TOKEN": "your_api_token_here"
      }
    }
  }
}

Available tools

pipefy_list_pipes

List available pipes and organizations for the authenticated user.

pipefy_get_pipe

Retrieve detailed information about a pipe, including phases, members, fields, and labels.

pipefy_list_cards

List cards in a specific pipe with optional search filters and limit.

pipefy_get_card

Get comprehensive details for a single card, including all field values.

pipefy_search_cards

Search cards by a specific field value within a pipe.

pipefy_create_card

Create a new card in a given pipe with specified fields and optional title.

pipefy_get_phase

Get details and fields for a specific phase in a pipe.

pipefy_list_tables

List database tables within an organization.

pipefy_get_table

Get detailed information about a database table, including fields and webhooks.

pipefy_create_table

Create a new database table within an organization.

pipefy_list_table_records

List records from a database table with optional limits.

pipefy_get_table_record

Retrieve a record from a table with all field values.

pipefy_create_table_record

Create a new record in a database table with specified fields.