Zapier SDK

Let your agent call actions across 9,000+ apps while Zapier holds the OAuth keys.

Source repo
zapier/sdk
Stars
★ 269
Last updated
25d ago
License
MIT

At a glance

How it runs
CLILibrary / SDKAgent plugin / skill
Works with
Portable with changesCodex · Claude CodeClaude.ai (Partial support)
Cost
Free tier plus a paid hosted plan
Setup effort
Medium · a few setup steps
You'll need
Node.jsnpm@zapier/zapier-sdk@zapier/zapier-sdk-clitypescriptShell / CLINetwork accessLocal filesystem
Typical use
An automation engineer connecting several SaaS tools who does not want to register and refresh OAuth apps per vendor — create connections once, then chain Notion, Gmail, Google Sheets, and Airtable calls.
Not a fit if
  • Teams that need fully offline or self-hosted operation: connections, credentials, and the action catalog all live in Zapier's cloud
  • Teams that cannot send data through a third-party SaaS: OAuth grants and action calls all go through Zapier
  • Teams onboarding many apps at once: each app needs its own create-connection plus a manual browser OAuth step

What does this agent do, and when should you use it?

Zapier SDK gives programs access to Zapier's app ecosystem through the npm package @zapier/zapier-sdk, and this repo bundles the SDK's docs, verified examples, and installable agent skills. The execution model is local-first: you authenticate once with npx zapier-sdk login, create an OAuth connection per app with create-connection, then invoke a catalog action with run-action; Zapier stores the credentials and resolves action schemas at runtime, so your code never touches a token. Beyond the SDK and CLI, the repo ships an agentskills.io-conformant zapier-sdk skill, a read-only zapier-sdk-explorer subagent that resolves exact app/action/field IDs, and an examples corpus indexed by app, domain, and pattern. It can be installed as a plugin into Claude Code, OpenAI Codex, and GitHub Copilot CLI, or cloned and referenced from rules files for other assistants. The boundary is clear: your code is portable, but connections and the action catalog live in Zapier.

The repository documents and distributes @zapier/zapier-sdk (runtime) and @zapier/zapier-sdk-cli (companion CLI). The flow: install both packages, run npx zapier-sdk login to store credentials locally, then let createZapierSdk() pick them up automatically. list-connections shows existing grants, create-connection <app> opens a browser to authorize an app such as notion, gmail, google-sheets, or airtable, and run-action <app> <action> --inputs '{...}' executes a catalog action and returns JSON — for example notion search page_by_title, gmail search message, google-sheets search lookup_row, airtable search findRecord. The examples directory is indexed three ways: by-app for single authenticated calls, by-domain READMEs that map a business domain to relevant examples, and by-pattern for end-to-end shapes like notify-on-event, data-sync, lead-routing, and scheduled-report. Every action key in the corpus is checked against listActions before inclusion. skills/zapier-sdk follows the agentskills.io spec, the zapier-sdk-explorer subagent investigates the live catalog before code is written, and sdk.fetch is the escape hatch for arbitrary HTTP APIs.

  1. An automation engineer connecting several SaaS tools who does not want to register and refresh OAuth apps per vendor — create connections once, then chain Notion, Gmail, Google Sheets, and Airtable calls.
  2. A developer configuring a coding assistant so it validates real action keys with zapier-sdk-explorer before generating SDK code, instead of inventing method names.
  3. A sales-ops or growth team doing lead routing: look up an Airtable record with findRecord by email and forward results to the next system.
  4. A reporting workflow that pulls rows from Google Sheets via lookup_row or messages from Gmail via search message and summarizes them on a schedule (the scheduled-report pattern).
  5. A support or ops person who wants a fast terminal check against an existing connection, e.g. Gmail query-syntax searches for messages from a specific sender.
  6. A team building its own agent runtime that loads the agentskills.io-conformant zapier-sdk skill as its tool-calling layer.

How do you install or deploy this agent?

Prerequisites: Node.js and npm (both the SDK and CLI are npm packages) and network access to Zapier.

1) Install the runtime SDK and dev dependencies (README commands as written):

npm install @zapier/zapier-sdk
npm install -D @zapier/zapier-sdk-cli @types/node typescript

2) Optional: install as a plugin for an AI coding assistant (commands reproduced from the README, including its spelling):
Claude Code:

/plugin marketplace add zapier/marketplace
/plugin install sdk@zapier

OpenAI Codex:

codex plugin marketplace add zapier/marketplace
codex plugin add sdk@zapier

GitHub Copilot CLI:

copilot plugin marketplace add zapier/marketplace
copilot plugin install sdk@zapier

3) For assistants without agentskills.io support:

git clone https://github.com/zapier/sdk.git

Then reference skills/zapier-sdk/SKILL.md from .cursorrules, AGENTS.md, or .github/copilot-instructions.md.

4) Authenticate with npx zapier-sdk login; credentials are stored on your machine and reused by createZapierSdk().

How do you use this agent?

Authenticate and check the profile:

npx zapier-sdk login
npx zapier-sdk get-profile

Add app connections (each opens a browser for OAuth):

npx zapier-sdk list-connections
npx zapier-sdk create-connection notion
npx zapier-sdk create-connection gmail
npx zapier-sdk create-connection google-sheets
npx zapier-sdk create-connection airtable

Run actions (JSON output):

npx zapier-sdk run-action notion search page_by_title --inputs '{"title":"Meeting Notes","exact_match":"no"}'
npx zapier-sdk run-action gmail search message --inputs '{"query":"from:[email protected]"}'
npx zapier-sdk run-action google-sheets search lookup_row --inputs '{"spreadsheet":"<sheet-id>","worksheet":"<tab-id>","lookup_key":"Email","lookup_value":"[email protected]"}'
npx zapier-sdk run-action airtable search findRecord --inputs '{"applicationId":"<base-id>","tableName":"Leads","searchByField":"Email","searchByValue":"[email protected]"}'

In code, call createZapierSdk() to reuse stored credentials, and use sdk.fetch for HTTP APIs without a first-class action. Browse examples/by-app/ for single-call patterns, docs.zapier.com/sdk/reference for the full method reference, and skills/zapier-sdk/references/cli-commands.md for the full CLI inventory.

What are this agent's strengths and limitations?

Pros
  • Zapier holds the OAuth grants, so you skip registering per-vendor OAuth apps and your code never sees a token
  • Example action keys are verified against listActions, giving the agent canonical, copy-paste-ready patterns
  • Ships both a runtime npm package and a CLI, so you can prototype with run-action and then move into code
  • Includes an agentskills.io-conformant skill plus a read-only zapier-sdk-explorer subagent that resolves exact app/action/field IDs first
  • Examples are indexed by app, domain, and pattern, covering one-off calls and multi-step automations
  • sdk.fetch provides a documented escape hatch for arbitrary HTTP APIs with no first-class action
Limitations
  • Core operation depends on the Zapier platform: connections, credentials, and the action catalog are all hosted there, with no self-hosted path
  • Requires Node.js and network access, and using the service is governed separately by Zapier's terms of service
  • The repository covers client code, docs, and examples only — the Zapier service itself is not open source
  • Pricing and rate limits are not stated in the repo; you must check zapier.com/sdk
  • Every app connection needs its own create-connection call and an interactive browser OAuth step, which is manual at scale
  • Worked examples require real spreadsheet, worksheet, or base IDs before they run successfully

How does this agent compare with similar options?

The repository names Zapier MCP (github.com/zapier/zapier-mcp) as the alternative: if your tool calling goes through the MCP protocol (Cursor, Claude Desktop, Codex), use the MCP server instead of this SDK and CLI.

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
Zapier SDK This agent 55 · Major gaps CLIFreemium ★ 269 25d ago — Codex · Claude Code
Uni-CLI 83 · Good CLIFree ★ 228 5d ago TypeScript ChatGPT · Codex · Claude Code
OSS Autopilot 80 · Good Agent plugin / skillFree ★ 28 today TypeScript Claude Code · Claude.ai
ZCF - Zero-Config Code Flow 71 · Some gaps CLIFree + model costs ★ 6.1k 10d ago TypeScript Codex · Claude Code

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
55/ 100 5-point scale 2.8 / 5
Trust 14/29
Reliability 6/14
Adaptability 12/18
Convention 10/18
Effectiveness 9/13
Verifiability 4/8
Why each dimension lost points
Trust14 / 29 · 2.4/5

The README and AGENTS.md say Zapier holds OAuth grants, connections are created with user authorization, and user tokens should not be stored; this supports the data-flow and sensitive-credential scores. Browser authorization requires user participation. Deductions: examples can cause external app changes, but the packet does not establish per-action confirmation, permission scope, revocation, or recovery guidance across the product. Dependency security is only evidenced by CI install steps, with no audit or vulnerability-response evidence. Repository identity and a security contact are stated, but publisher identity is not independently verified by the supplied material.

Reliability6 / 14 · 2.1/5

The packet describes structural checks, workflow typechecks, CLI/SDK smoke steps, and an optional live-catalog audit. Deductions: README and skill references differ in specific filenames and usage details, and the audit skips when credentials are unavailable; this static review cannot establish that checks passed. Failure and recovery guidance is limited, mostly to a nonzero-exit note for profile lookup.

Adaptability12 / 18 · 3.3/5

The skill distinguishes SDK code, one-off CLI use, MCP tool calling, and durable workflows, and names scenarios and trigger phrases. AGENTS.md says to inspect dynamic inputs against a live connection and identifies raw HTTP as an escape hatch. Deductions: environment guidance focuses on Node/TypeScript and several coding assistants, with limited coverage of other runtimes or out-of-scope cases.

Convention10 / 18 · 2.8/5

The README, skill references, and examples are organized by app, domain, and workflow pattern, with install, authentication, connection, and example entry points. The MIT license text is present. Deductions: version details are scattered and no changelog is included in the packet; maintenance responsibility is only partly described through contribution guidance, repository references, and a security email; known limitations cover only some dynamic fields and human OAuth steps.

Effectiveness9 / 13 · 3.5/5

The repository offers copyable commands, TypeScript examples, and live action discovery guidance that can reduce guessing about app keys, action keys, and input shapes. Deductions: examples include search, send, or write operations against external services, so value depends on the user's connections and action permissions; no time or operating-cost evidence is supplied.

Verifiability4 / 8 · 2.5/5

Setup and architecture claims point to repository materials; the README identifies a demo transcript source, and AGENTS.md identifies an audit script and describes CI action-key checks. Deductions: the supplied packet omits the audit script, transcript contents, and full examples, preventing cross-source validation; CI configuration evidences intended checks, not successful execution.

Risks and how to mitigate them
  • Before running an example, verify the target app, connection, and inputs; write or send actions may change user data or deliver content externally.
  • An OAuth connection grants Zapier access to the relevant app; review its scope and revoke it through Zapier or the app when no longer needed.
  • This assessment uses only the supplied static material; it does not verify the live catalog, CI results, or runtime behavior.
Evidence confidence: Low Reviewed Nov 08, 2026 Reviewed revision 2b37ff9104fb
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/sdk.svg)](https://followagents.com/en/agents/sdk)
<a href="https://followagents.com/en/agents/sdk"><img src="https://followagents.com/badge/sdk.svg" alt="FARS review"></a>

FAQ

Do I need to register and store OAuth credentials for each app myself?
No. Zapier holds the OAuth grants; you create a connection with npx zapier-sdk create-connection <app> and your code never touches a token.
What runtime does it need?
Node.js and npm to install @zapier/zapier-sdk and @zapier/zapier-sdk-cli, plus network access to Zapier at run time; login credentials live on your local filesystem.
What happens if a call fails because the action key is wrong?
The corpus keys are checked against listActions. Resolve the exact app/action/field ID first with the zapier-sdk-explorer subagent or the CLI, then run run-action; if no first-class action exists, use sdk.fetch against the underlying HTTP API.
How does this relate to Zapier MCP?
This repo targets code and CLI usage (npm package, the zapier-sdk CLI, and the agentskills.io skill); Zapier MCP is the MCP-server alternative for tool calling from Cursor, Claude Desktop, or Codex.
What are the licensing and cost boundaries?
MIT covers the repository code only. Using Zapier's service and APIs through the SDK is governed by Zapier's Terms of Service or your other agreement with Zapier; pricing and quotas are on zapier.com/sdk.
Was this page helpful?
View on GitHub ↗ Install ↓

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.