Pipefy

v1.0.0Business Applicationsstable

MCP server, CLI, and agent skills for Pipefy.

pipefymcpai-integration
Share:
20
Stars
0
Downloads
0
Weekly
0/5

What is Pipefy?

Pipefy is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server, cli, and agent skills for pipefy.

MCP server, CLI, and agent skills for Pipefy.

This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP server, CLI, and agent skills for Pipefy.

Use Cases

Manage Pipefy workflow processes through CLI and agent skills. Create and track tasks and processes programmatically.
gbrlcustodio

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx pipefy

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Pipefy

The Pipefy AI Toolkit is an MCP server, CLI, and agent skill suite that gives AI assistants full programmatic access to the Pipefy workflow automation platform. It exposes 149 tools across ten domains — including pipes, cards, database tables, reports, automations, portals, and webhooks — enabling AI agents to create, read, update, and manage every aspect of Pipefy workflows. Teams using Pipefy for business process management can automate repetitive operations and build AI-driven workflow assistants without writing custom API integrations.

Prerequisites

  • A Pipefy account with appropriate admin or user permissions
  • Python 3.11+ with uv package manager installed (for CLI installation)
  • Or: Claude Code with the Pipefy plugin installed from the marketplace
  • PIPEFY_TOKEN or Pipefy service account credentials for authentication
  • An MCP-compatible client: Claude Desktop, Cursor, or Claude Code
1

Install the Pipefy AI Toolkit via the quick-install script

Run the official installer script, specifying your client type (cursor, claude, etc.). This installs the CLI and registers the MCP server automatically.

curl -fsSL https://raw.githubusercontent.com/pipefy/ai-toolkit/main/install.sh | sh -s -- --client cursor
2

Authenticate with your Pipefy account

Log in interactively using the CLI. This opens a browser OAuth flow and stores your session securely in the OS keychain. For CI or unattended use, set PIPEFY_TOKEN or service account credentials as environment variables instead.

pipefy auth login
3

Verify the connection by listing your pipes

Run a quick CLI command to confirm authentication is working and the MCP server can reach the Pipefy API.

pipefy pipe list --json
4

Configure the MCP server in your AI client

For manual MCP client setup, add the Pipefy server configuration. Use PIPEFY_TOKEN for service account or headless environments.

{
  "mcpServers": {
    "pipefy": {
      "command": "pipefy",
      "args": ["mcp"],
      "env": {
        "PIPEFY_TOKEN": "your-pipefy-api-token"
      }
    }
  }
}
5

Use the 149 MCP tools through your AI assistant

With the MCP server connected, your AI can now list pipes, create cards, query database tables, generate reports, and manage automations. Destructive operations require explicit --yes confirmation.

# Example CLI commands (also available as MCP tools):
pipefy pipe list --json
pipefy card get 123456789
pipefy introspect query --name getPipe

Pipefy Examples

Client configuration

MCP server configuration for Claude Desktop or Cursor using a Pipefy API token.

{
  "mcpServers": {
    "pipefy": {
      "command": "pipefy",
      "args": ["mcp"],
      "env": {
        "PIPEFY_TOKEN": "your-pipefy-api-token"
      }
    }
  }
}

Prompts to try

Example prompts to use with the Pipefy MCP server in Claude Desktop or Cursor.

- "List all pipes in my Pipefy organization"
- "Create a new card in the Sales pipeline with title 'Follow up with Acme Corp'"
- "Show me all cards in the 'In Progress' phase of the Support pipe"
- "Generate a report for the Onboarding pipe showing cards completed this month"
- "Set up a webhook on the HR pipe to notify Slack when a card moves to Done"

Troubleshooting Pipefy

Authentication fails with 'unauthorized' error

Run 'pipefy auth login' to refresh your session. For service account use, ensure PIPEFY_TOKEN or PIPEFY_SERVICE_ACCOUNT_CLIENT_ID/SECRET are set correctly in the environment. Tokens can be generated in Pipefy Admin under API tokens.

MCP server not found after installation

Verify the pipefy CLI is in your PATH by running 'which pipefy'. If using uv tool install, run 'uv tool list' to confirm installation. You may need to add the uv tools bin directory to your PATH.

Destructive operations (delete, move) are blocked

Destructive operations require explicit confirmation. When running via CLI, append '--yes' to the command. When using the MCP server, instruct the AI agent to confirm the action explicitly before proceeding.

Frequently Asked Questions about Pipefy

What is Pipefy?

Pipefy is a Model Context Protocol (MCP) server that mcp server, cli, and agent skills for pipefy. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Pipefy?

Follow the installation instructions on the Pipefy GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Pipefy?

Pipefy works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Pipefy free to use?

Yes, Pipefy is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Pipefy Alternatives — Similar Business Applications Servers

Looking for alternatives to Pipefy? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.

n8n

189.1k

A comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou

LobeHub

77.5k

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

Jeecgboot

46.4k

AI 低代码平台,「低代码 + 零代码」双模式驱动:低代码一键生成前后端代码,零代码 5 分钟搭建系统,AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等,兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式,消除 Java 项目 80% 的重复工作,提效而不失灵活。

CowAgent

44.7k

CowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入,可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI,能处理文本、语音、图片和文件,可快速搭建个人AI助理和企业数字员工。

Minds Platform

39.2k

Platform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.

Astrbot

32.8k

AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

Browse More Business Applications MCP Servers

Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "pipefy": { "command": "npx", "args": ["-y", "pipefy"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Pipefy?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides