https://github.com/pipefy/ai-toolkit

MCP server, CLI, and agent skills for Pipefy.
https://github.com/pipefy/ai-toolkit
ai-toolkit cli mcp-server pipefy sdk skills
Last synced: 19 days ago
JSON representation
MCP server, CLI, and agent skills for Pipefy.
Host: GitHub
URL: https://github.com/pipefy/ai-toolkit
Owner: pipefy
Created: 2025-04-08T21:42:59.000Z (about 1 year ago)
Default Branch: main
Last Pushed: 2026-06-03T01:48:46.000Z (22 days ago)
Last Synced: 2026-06-03T03:17:15.939Z (22 days ago)
Topics: ai-toolkit, cli, mcp-server, pipefy, sdk, skills
Language: Python
Homepage:
Size: 2.08 MB
Stars: 24
Watchers: 1
Forks: 8
Open Issues: 27
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- Agents: AGENTS.md
Awesome Lists containing this project

README

          


  





  

  

  

  

  



# pipefy-labs

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.



  Overview •

  Installation •

  Repository layout •

  MCP server •

  CLI •

  Agent skills •

  Documentation •

  Development •

  Contributing



---

## Overview

| Component | Package / path | Purpose |

|-----------|----------------|---------|

| **MCP server** | `pipefy-mcp-server` | Exposes **149** tools to MCP clients (Cursor, Claude Desktop, Claude Code, and others). |

| **CLI** | `pipefy-cli` | Terminal commands aligned with MCP capabilities; see [`docs/parity.md`](docs/parity.md). |

| **SDK** | `pipefy-sdk` | Vendor GraphQL client, services, and models shared by MCP and CLI. |

| **Skills** | [`skills/`](skills/) | Markdown playbooks (Anthropic Skills format) for common Pipefy workflows. |

Feedback and issues: [GitHub Issues](https://github.com/pipefy/ai-toolkit/issues) · **dev@pipefy.com**

---

## Installation

> 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`](https://github.com/pipefy/ai-toolkit/releases/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](https://app.pipefy.com/) (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`](docs/config.md).

### Quick install (recommended)

One command installs the CLI + MCP server, optionally adds skills, and registers the MCP server in your client config:

```sh

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](https://github.com/pipefy/ai-toolkit/releases) 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"}`.

### Claude Code

```text

/plugin marketplace add pipefy/ai-toolkit

/plugin install pipefy

/pipefy:install

/pipefy:login

```

`/plugin install pipefy` registers the MCP server and the `/pipefy:install` + `/pipefy:login` slash commands. `/pipefy:install` runs `uv tool install` once to put `pipefy` on PATH (idempotent). `/pipefy:login` runs the OAuth browser flow. For hand-wired setups (paste-into-config blocks per client, the macOS `errSecParam` keychain note, the local-clone alternative for contributors), see [`packages/mcp/README.md`](packages/mcp/README.md).

### CLI

Ad-hoc:

```sh

uvx \

  --with "pipefy-sdk @ git+https://github.com/pipefy/ai-toolkit@latest#subdirectory=packages/sdk" \

  --with "pipefy-auth @ git+https://github.com/pipefy/ai-toolkit@latest#subdirectory=packages/auth" \

  --from "git+https://github.com/pipefy/ai-toolkit@latest#subdirectory=packages/cli" \

  pipefy-cli --help

```

Permanent install:

```sh

uv tool install \

  --with "pipefy-sdk @ git+https://github.com/pipefy/ai-toolkit@latest#subdirectory=packages/sdk" \

  --with "pipefy-auth @ git+https://github.com/pipefy/ai-toolkit@latest#subdirectory=packages/auth" \

  "git+https://github.com/pipefy/ai-toolkit@latest#subdirectory=packages/cli"

pipefy --install-completion bash    # or zsh, fish

pipefy auth login                   # browser OAuth, session in OS keychain

```

CLI deep-dives (auth precedence, `--token` / `PIPEFY_TOKEN`, parity matrix): [`packages/cli/README.md`](packages/cli/README.md) and [`docs/cli/`](docs/cli/README.md).

### Skill catalog install

```sh

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`](skills/README.md).

### Post-1.0 (PyPI preview)

```sh

uvx pipefy-mcp-server

uv tool install pipefy-cli

```

Deprecation and semver (post-1.0): [`docs/DEPRECATION.md`](docs/DEPRECATION.md).

---

## Repository layout

`uv` workspace with three Python packages and a skills catalog. **`pipefy-sdk`** is the vendor GraphQL layer; MCP and CLI depend on it and do not import each other.

| Path | Distribution | Role |

|------|--------------|------|

| [`packages/sdk/`](packages/sdk/) | `pipefy-sdk` | GraphQL transport, services, queries, Pydantic models. [Package README](packages/sdk/README.md) |

| [`packages/mcp/`](packages/mcp/) | `pipefy-mcp-server` | MCP tool registration and server lifecycle. [Package README](packages/mcp/README.md) |

| [`packages/cli/`](packages/cli/) | `pipefy-cli` | Typer CLI (`pipefy` command). [Package README](packages/cli/README.md) |

| [`skills/`](skills/) | — | Agent skill playbooks. [Catalog](skills/README.md) |

---

## MCP server

The server registers **149 tools** across ten domains. Canonical names: `PIPEFY_TOOL_NAMES` in [`packages/mcp/src/pipefy_mcp/tools/registry.py`](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`](docs/mcp/tools/cross-cutting.md).

| Domain | Tools | Summary | Reference |

|--------|:-----:|---------|-----------|

| **Pipes & cards** | 37 | Pipes, phases, fields, labels, cards, field conditions, attachments. | [docs](docs/mcp/tools/pipes-and-cards.md) |

| **Database tables** | 17 | Tables, records, schema, table-record attachments. | [docs](docs/mcp/tools/database-tables.md) |

| **Relations** | 8 | Pipe and card relations. | [docs](docs/mcp/tools/relations.md) |

| **Reports** | 17 | Pipe and organization reports, async exports. | [docs](docs/mcp/tools/reports.md) |

| **Automations & AI** | 22 | Automations, AI automations, AI agents, validators. | [docs](docs/mcp/tools/automations-and-ai.md) |

| **Observability** | 10 | Logs, usage, credits, job exports. | [docs](docs/mcp/tools/observability.md) |

| **Members, email & webhooks** | 11 | Membership, inbox email, webhooks. | [docs](docs/mcp/tools/members-email-webhooks.md) |

| **Organization** | 1 | Organization metadata. | [docs](docs/mcp/tools/organization.md) |

| **Portals** | 20 | Portal read/CRUD, pages, elements, sub-portals (publish/unpublish). | [docs](docs/mcp/tools/portal.md) |

| **Introspection** | 5 | Schema discovery and raw GraphQL. | [docs](docs/mcp/tools/introspection.md) |

---

## Command-line interface

The **`pipefy`** CLI mirrors shipped MCP capabilities where parity is defined in **[`docs/parity.md`](docs/parity.md)**. Conventions: Rich output by default, **`--json`** for scripts, **`--yes`** on destructive commands.

```sh

pipefy pipe list --json

pipefy card get 123456789

pipefy introspect query --name getPipe

```

CLI-specific guides: **[`docs/cli/`](docs/cli/README.md)** (including [introspect-then-execute](docs/cli/self-healing.md)).

---

## Agent skills

The [`skills/`](skills/) directory holds workflow playbooks: prerequisites, tool tables (MCP + CLI), steps, and success criteria. Compatible with any agent that reads Markdown (Cursor, Claude Code, Codex, and others). Distribution is via [`skills.sh`](https://github.com/vercel-labs/skills) (55+ agent targets); install commands are under [Installation](#installation) above.

Full catalog: [`skills/README.md`](skills/README.md). Authoring: [`skills/AGENTS.md`](skills/AGENTS.md). Contributions: [`CONTRIBUTING.md`](CONTRIBUTING.md).

---

## Documentation

| Document | Description |

|----------|-------------|

| [`docs/README.md`](docs/README.md) | Index by surface (MCP, CLI, SDK). |

| [`docs/config.md`](docs/config.md) | `PIPEFY_*` environment variables, `config.toml` schema and path, precedence chain. |

| [`docs/parity.md`](docs/parity.md) | MCP tool ↔ CLI command matrix. |

| [`docs/MIGRATION.md`](docs/MIGRATION.md) | Notes for existing MCP users. |

| [`AGENTS.md`](AGENTS.md) | Repository guidelines for contributors and agents. |

| [`RELEASE.md`](RELEASE.md) | Versioning and release process. |

---

## Development

Install [`uv`](https://docs.astral.sh/uv/getting-started/installation/) if you don't have it, then from the repository root:

```bash

uv sync

[[ -f .env ]] || cp .env.example .env   # first-time setup; then fill in PIPEFY_SERVICE_ACCOUNT_*

uv run pytest -m "not integration"    # unit tests (no live API)

uv run pytest -m integration -v     # live API (requires PIPEFY_*)

uv run ruff check . && uv run ruff format .

```

**MCP Inspector** (protocol debugging):

```bash

npx @modelcontextprotocol/inspector uv --directory . run pipefy-mcp-server

```

**Adding an MCP tool:** implement under `packages/mcp/src/pipefy_mcp/tools/`, register in `ToolRegistry`, add the name to `PIPEFY_TOOL_NAMES`, and ship the matching CLI command (or document a deferral in `docs/parity.md`). See [`AGENTS.md`](AGENTS.md) for the full TDD workflow.

---

## Contributing

Contributions are welcome via issues and pull requests.

| Area | How to contribute |

|------|-------------------|

| **Skills** | Markdown only — see [`CONTRIBUTING.md`](CONTRIBUTING.md). |

| **MCP / CLI / SDK** | Follow [`AGENTS.md`](AGENTS.md) and [`docs/parity.md`](docs/parity.md). |

| **Field mapping gaps** | Open an issue with the field type and expected behavior. |

| **Existing MCP setups** | [`docs/MIGRATION.md`](docs/MIGRATION.md) — configuration remains compatible. |
ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

https://github.com/pipefy/ai-toolkit

Awesome Lists containing this project

README
