MCP server for Pipefy

Name: MCP server for Pipefy
Author: gbrlcustodio

@gbrlcustodio

リポジトリ

MCP server for Pipefy について

MCP server, CLI, and agent skills for Pipefy.

基本情報

カテゴリ

その他

ランタイム

python

トランスポート

stdio

公開者

gbrlcustodio

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "pipefy-mcp-server": {
      "command": "uv",
      "args": [
        "tool",
        "install",
        "\\"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MCP server for Pipefy?

The MCP server for Pipefy is an open-source component of the Pipefy AI Toolkit that exposes 152 tools to Model Context Protocol (MCP) clients like Cursor, Claude Desktop, and Claude Code. It enables AI agents to interact programmatically with Pipefy, a workflow automation platform, covering pipes, cards, reports, automations, databases, portals, and more.

How to use MCP server for Pipefy?

Install via the recommended quick install script (curl -fsSL ... | sh) or through the Claude Code plugin marketplace. After installation, authenticate using either human OAuth (pipefy auth login) or a service account (set PIPEFY_SERVICE_ACCOUNT_CLIENT_ID and PIPEFY_SERVICE_ACCOUNT_CLIENT_SECRET). Configure your MCP client to run the pipefy-mcp-server command. The server is used by connecting any MCP-compatible client to the running server process.

Key features of MCP server for Pipefy

152 tools across ten domains (pipes & cards, databases, reports, automations, etc.)
Supports both human OAuth and service account authentication
Part of a larger open-source toolkit (CLI, SDK, agent skill playbooks)
Compatible with any MCP client (Cursor, Claude Desktop, Claude Code, Codex)
Ships with a skill catalog of workflow playbooks for common Pipefy tasks
Open source under Apache 2.0 license

Use cases of MCP server for Pipefy

Automate Pipefy workflows via AI agents (e.g., creating cards, moving phases)
Query and manage Pipefy database tables and records programmatically
Generate and export reports, logs, and usage data
Manage memberships, webhooks, and portal content
Perform introspection and execute raw GraphQL queries

FAQ from MCP server for Pipefy

What are the runtime dependencies?

Python 3.11+ and the uv package manager are required. The server is distributed via uvx or uv tool install from the git repository (pre-1.0) or PyPI (post-1.0).

How do I authenticate with MCP server for Pipefy?

Two authentication paths exist: human OAuth (interactive browser flow, stores session in OS keychain) and service account (unattended/CI, using PIPEFY_SERVICE_ACCOUNT_CLIENT_ID and PIPEFY_SERVICE_ACCOUNT_CLIENT_SECRET environment variables).

Does the MCP server for Pipefy depend on the CLI or SDK?

No, the MCP server (pipefy-mcp-server) depends on the shared pipefy-sdk package but does not import the CLI. The SDK provides the GraphQL client and models used by both.

What transport does the server use?

The server follows the Model Context Protocol standard. The default transport is stdio, compatible with most MCP clients like Claude Desktop and Claude Code.