Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Zapier MCP plugin for AI clients
This repo distributes the client-side plugin for Zapier's hosted MCP server. It lets supported agents connect to Zapier, then layers onboarding, a demo, and role-specific skills onto that connection.
Builders who want their agent to connect to thousands of apps through Zapier.
You can let your agent send messages, pull data, and trigger workflows across Zapier-connected apps without building the integration yourself.
What it does
Client-side plugin distribution
Packages the Zapier MCP plugin that you install in supported AI clients.
Guided onboarding
Helps the assistant start using Zapier MCP with a setup flow inside the client.
First-use demo
Shows a demo the first time you connect so the assistant knows what Zapier can do.
Role-tailored skills
Adds skills tuned to the user's role on top of the base MCP connection.
Hosted MCP server connection
Connects to Zapier's hosted MCP endpoint at `https://mcp.zapier.com/api/v1/connect`.
Gemini extension support
Includes `gemini-extension.json` for Gemini CLI extension installation.
README

Zapier MCP Plugin Distribution
Zapier MCP gives any MCP-compatible AI client governed access to 9,000+ apps — send messages, pull data, trigger workflows, all in plain English. No code, no infrastructure, SOC 2 Type II certified. ⚡
This repo distributes the Zapier MCP plugin — the part that lives in your AI client. Install it from your client's marketplace and your assistant arrives knowing how to use Zapier well, with guided onboarding, a quick demo, and skills tailored to your role.

What's in this repo
plugins/zapier/: the plugin that onboards you to Zapier MCP and supercharges your experience
Getting started
Connecting Zapier MCP to your AI client only takes a server URL — see docs.zapier.com/mcp/clients for step-by-step instructions for every supported client.
A few clients also install the plugin distributed from this repo, which layers guided onboarding, a first-use demo, and role-tailored skills on top of that base connection:
- Claude Code: add
zapier/marketplaceoranthropics/claude-plugins-official - Cursor: use the badge above, or add
cursor/mcp-servers - OpenAI Codex and GitHub Copilot CLI: add
zapier/marketplace - Claude Cowork: add
anthropics/knowledge-work-plugins - Kiro: via kiro.dev/powers
- Gemini CLI:
gemini extensions install https://github.com/zapier/zapier-mcp, then/mcp auth zapier— seegemini-extension.json
VS Code connects directly to the hosted MCP server rather than through a plugin — use the badge above, or add https://mcp.zapier.com/api/v1/connect (type: http) manually.
Third-party registries
Zapier MCP is also listed on:
For contributors
- AGENTS.md: guide for AI agents working in this repo
- CONTRIBUTING.md: how to contribute
- llms.txt: LLM discovery index
Files in the repo
- assets
- plugins
- zapier-power
- .gitignore
- AGENTS.md
- CLAUDE.md
- CONTRIBUTING.md
- gemini-extension.json
- LICENSE
- llms.txt
- README.md
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More plugins

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Opinionated Oxlint rules for rejecting low-evidence TypeScript and JavaScript patterns
Teams-first Multi-agent orchestration for Claude Code