MCP server for Pipefy
About
MCP server, CLI, and agent skills for Pipefy.
Explore
- 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
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP server for PipefyCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
> Pre-1.0 ships from this git repo via uvx and uv tool install. PyPI becomes the canonical source at v1.0. The current beta line is v0.2.0-beta.* (first tag: v0.2.0-beta.1). Two install paths: the Quick install script below (resolves the latest GitHub Release at runtime and runs uv tool install for you), or Claude Code via the plugin marketplace.
>
> The CLI snippets below pin @latest, a moving git tag the release flow updates to point at the most recent release. To pin a specific version, swap @latest for a version tag (e.g. @v0.2.0-beta.2). The --with pipefy-sdk @ ...#subdirectory=packages/sdk / pipefy-auth @ ...#subdirectory=packages/auth flags are required pre-1.0: this repo is a uv workspace, and the workspace members are not yet published to PyPI, so uv needs them named explicitly. The flags go away at v1.0 (PyPI install).
Two auth paths:
- Human OAuth (interactive): pipefy auth login runs the browser flow and stores a session in your OS keychain. Works anywhere the pipefy CLI is on PATH (uv tool install once, any client can invoke it). Claude Code additionally exposes it as the /pipefy:login slash command via the plugin marketplace. Pipe membership is whatever the signed-in user already has.
- Service account (unattended / CI): provision a Service Account in Pipefy Admin (Admin → Service Accounts) and add that account to every pipe the tools should touch. Wire PIPEFY_SERVICE_ACCOUNT_CLIENT_ID and PIPEFY_SERVICE_ACCOUNT_CLIENT_SECRET into the client config below.
Full env-var reference and config.toml precedence: docs/config.md.
One command installs the CLI + MCP server, optionally adds skills, and registers the MCP server in your client config:
curl -fsSL https://raw.githubusercontent.com/pipefy/ai-toolkit/main/install.sh \
| sh -s -- --client cursor
Replace --client cursor with one of: claude-code, claude-desktop, codex, or none (prints the snippet to paste). Useful flags:
- --yes skip all confirmation prompts.
- --no-skills skip the npx skills add step.
- --version vX.Y.Z pin a specific GitHub Release tag (default: most recent prerelease or release).
- --dry-run print every command without executing.
- --allow-root opt-in for root execution (refused by default).
After install, run pipefy auth login to authenticate (--device on headless systems). The installer puts pipefy-mcp-server on PATH, so each client's config collapses to {"command": "pipefy-mcp-server"}.
npx skills add pipefy/ai-toolkit # all skills
npx skills add pipefy/ai-toolkit --skill pipefy-pipes-and-cards
Catalog and authoring guide: skills/README.md.
Open-source toolkit for Pipefy developers: a Model Context Protocol (MCP) server for AI agents, a pipefy CLI for terminals and automation, a shared GraphQL SDK, and a catalog of agent skill playbooks.
<p align="center">
<a href="#overview">Overview</a> •
<a href="#installation">Installation</a> •
<a href="#repository-layout">Repository layout</a> •
<a href="#mcp-server">MCP server</a> •
<a href="#command-line-interface">CLI</a> •
<a href="#agent-skills">Agent skills</a> •
<a href="#documentation">Documentation</a> •
<a href="#development">Development</a> •
<a href="#contributing">Contributing</a>
</p>
---
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp server for pipefy": {
"pipefy-mcp-server": {
"command": "uv",
"args": [
"tool",
"install",
"\\"
]
}
}
}
}McpServers
{
"pipefy-mcp-server": {
"command": "uv",
"args": [
"tool",
"install",
"\\"
]
}
}The server registers 152 tools across ten domains. Canonical names: PIPEFY_TOOL_NAMES in packages/mcp/src/pipefy_mcp/tools/registry.py.
Tool descriptions and Args: blocks come from Python docstrings (what MCP clients show to models). Per-area reference docs cover parameters, edge cases, and cross-cutting behavior.
Shared conventions (pagination, IDs, permissions, error shape): docs/mcp/tools/cross-cutting.md.
| Domain | Tools | Summary | Reference |
|--------|:-----:|---------|-----------|
| Pipes & cards | 40 | Pipes, phases, fields, labels, cards, field conditions, attachments. Phase inventory (get_phase_cards, get_phase_cards_count), move discovery (get_phase_allowed_move_targets), and create_card(phase_id=…) reduce raw GraphQL for agent seeding. | docs |
| Database tables | 17 | Tables, records, schema, table-record attachments. | docs |
| Relations | 8 | Pipe and card relations. | docs |
| Reports | 17 | Pipe and organization reports, async exports. | docs |
| Automations & AI | 23 | Automations, AI automations, AI agents, validators. | docs |
| Observability | 10 | Logs, usage, credits, job exports. | docs |
| Members, email & webhooks | 11 | Membership, inbox email, webhooks. | docs |
| Organization | 1 | Organization metadata. | docs |
| Portals | 20 | Portal read/CRUD, pages, elements, sub-portals (publish/unpublish). | docs |
| Introspection | 5 | Schema discovery and raw GraphQL. | docs |
---
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
