Install
npm install -g zapier-platform-cli
vs n8n
vs Make
vs Temporal
vs WindmillShowcase
Try itExperimental
See what an agent can do with Zapier before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).
$zapier-platform --versionrecorded session — replayed, not liveVerified integrations
Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.
AsanaProject Management
Cal.comScheduling & Calendar
ChatGPTAI Assistants
ClaudeAI Assistants
CursorAI Coding AgentsFinAI Customer Support Agents
Otter.aiMeeting AI & Notetakers
PipedreamWorkflow Automation
Salesforce Sales CloudCRM
SavvyCalScheduling & Calendar
ShortwaveEmail Clients & Email AI
SkyvernBrowser Automation for Agents
SlackTeam Chat
TwentyCRM
ZulipTeam ChatBy theme — the product's score on each story themeBy theme
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Ai workflows — AI in the engine loop — agent-driven editors, copilots, codegen-friendly APIs, runtime inferenceAi workflowsevidence →
AI in the engine loop — agent-driven editors, copilots, codegen-friendly APIs, runtime inference
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Code extensibility — stories about code extensibility in this arenaCode extensibilityevidence →
Stories about code extensibility in this arena
Collaboration governance — stories about collaboration governance in this arenaCollaboration governanceevidence →
Stories about collaboration governance in this arena
Connectors ecosystem — stories about connectors ecosystem in this arenaConnectors ecosystemevidence →
Stories about connectors ecosystem in this arena
Deployment embedding — stories about deployment embedding in this arenaDeployment embeddingevidence →
Stories about deployment embedding in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Reliability errors — stories about reliability errors in this arenaReliability errorsevidence →
Stories about reliability errors in this arena
Triggers scheduling — stories about triggers scheduling in this arenaTriggers schedulingevidence →
Stories about triggers scheduling in this arena
Visual builder — stories about visual builder in this arenaVisual builderevidence →
Stories about visual builder in this arena
Story verdicts — every judged story with its evidenceStory verdicts
What’s free: 1 free · 4 paid · 0 enterprise · 24 not stated in evidence
Follow the green: where the map greys out is where Zapier stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
~6/10
unlocks → Machine-readable spec · Versioning policy · API sandbox · Full data export · Drop into real code (JavaScript or Python) as a step inside a workflow · Map and transform data between steps with expressions, functions, or formulas · Start from a public library of workflow templates instead of building from scratch
Subscribe to events via webhooks
✓8/10
Build against official SDKs
~6/10
Issue scoped/least-privilege API credentials for an agent
~5/10
Connect an agent via an official MCP server
✓8/10
Download a machine-readable API spec (OpenAPI or equivalent)
—0/10
Rely on versioned APIs with a documented deprecation policy
—0/10
Test against a sandbox environment without touching production data
—–
Explore an interactive API reference with runnable examples
—0/10
Docs for agents
Point an agent at llms.txt or agent-oriented docs
✓9/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
~6/10
unlocks → MCP client
Operate the product with natural-language commands
✓8/10
Plug MCP servers into this product so it can use their tools
—0/10
Get AI-generated insights and suggestions from my data inside the product
~4/10
Set up automations that run autonomously in the background
✓8/10
Ai workflows — AI in the engine loop — agent-driven editors, copilots, codegen-friendly APIs, runtime inferenceAi workflows
AI in the engine loop — agent-driven editors, copilots, codegen-friendly APIs, runtime inference
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Automation depth
Define rules that trigger actions automatically on events
✓8/10
unlocks → Versioned workflows · Run workflows on cron-style schedules with timezone control
Schedule recurring jobs or workflows
~4/10
unlocks → Versioned workflows
Perform bulk operations across many items at once
—0/10
Version, review, and roll back my automations
—–
Code extensibility — stories about code extensibility in this arenaCode extensibility
Stories about code extensibility in this arena
Collaboration governance — stories about collaboration governance in this arenaCollaboration governance
Stories about collaboration governance in this arena
Connectors ecosystem — stories about connectors ecosystem in this arenaConnectors ecosystem
Stories about connectors ecosystem in this arena
Deployment embedding — stories about deployment embedding in this arenaDeployment embedding
Stories about deployment embedding in this arena
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Reliability errors — stories about reliability errors in this arenaReliability errors
Stories about reliability errors in this arena
Durability
Error handling
Inspect past execution logs and re-run a failed execution, resuming from the failing step
—0/10
Triggers scheduling — stories about triggers scheduling in this arenaTriggers scheduling
Stories about triggers scheduling in this arena
Visual builder — stories about visual builder in this arenaVisual builder
Stories about visual builder in this arena
Sorted by importance (agentic first) (high → low) · 56/56 stories · click a row’s chevron for the rationale and evidence
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 8/10 | Tprobed | |
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | partial | 6/10 | Cclaimed | |
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | partial | 6/10 | Tprobed | |
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | 0/10 | ||
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 9/10 | Tprobed | |
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Xcommunity | |
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 6/10 | Tprobed | |
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Cclaimed | |
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Tprobed | |
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 4/10 | Cclaimed | |
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | none | untested | none yet | |
Build multi-step workflows in a visual editor without writing code C Builder | ops user | Visual builder — stories about visual builder in this arenaVisual builder | 3 | fullpaid | 9/10 | Xcommunity | |
Connect to thousands of apps through prebuilt, vendor-maintained integrations C Connectors | ops user | Connectors ecosystem — stories about connectors ecosystem in this arenaConnectors ecosystem | 3 | fullpaid | 9/10 | Xcommunity | |
Trigger workflows from events in connected apps (new record, message, email, form submission) C Triggers | ops user | Triggers scheduling — stories about triggers scheduling in this arenaTriggers scheduling | 3 | fullpaid | 9/10 | Xcommunity | |
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | fullpaid | 8/10 | Xcommunity | |
Expose a custom webhook URL that receives external HTTP requests and starts a workflow run with the payload G Triggers | developer | Triggers scheduling — stories about triggers scheduling in this arenaTriggers scheduling | 3 | full | 8/10 | Xcommunity | |
Expose my workflows or connected app actions as MCP tools that an external agent can call C Agent integration | ai-native user | Ai workflows — AI in the engine loop — agent-driven editors, copilots, codegen-friendly APIs, runtime inferenceAi workflows | 3 | full | 8/10 | Tprobed | |
Store connection credentials centrally, share them with my team, and control who can use which credential C Credentials | ops user | Collaboration governance — stories about collaboration governance in this arenaCollaboration governance | 3 | partial | 6/10 | Cclaimed | |
Add AI agent or LLM steps inside a workflow, with model choice and tool use C Ai steps | ai-native user | Ai workflows — AI in the engine loop — agent-driven editors, copilots, codegen-friendly APIs, runtime inferenceAi workflows | 3 | partial | 5/10 | Cclaimed | |
Configure automatic retries with backoff for failed steps or activities C Error handling | developer | Reliability errors — stories about reliability errors in this arenaReliability errors | 3 | none | 0/10 | ||
Drop into real code (JavaScript or Python) as a step inside a workflow C Code steps | developer | Code extensibility — stories about code extensibility in this arenaCode extensibility | 3 | none | 0/10 | ||
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | none | untested | none yet | |
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | none | untested | none yet | |
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | none | untested | none yet | |
Build a custom connector or private integration with a documented developer platform, SDK, or CLI G Connector dev | developer | Code extensibility — stories about code extensibility in this arenaCode extensibility | 2 | full | 9/10 | Tprobed | |
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | partial | 5/10 | Tprobed | |
Generate or edit a workflow from a natural-language prompt C Ai authoring | ai-native user | Ai workflows — AI in the engine loop — agent-driven editors, copilots, codegen-friendly APIs, runtime inferenceAi workflows | 2 | partial | 5/10 | Cclaimed | |
Define dedicated error-handling paths or error workflows and get notified when a run fails C Error handling | ops user | Reliability errors — stories about reliability errors in this arenaReliability errors | 2 | partial | 4/10 | Cclaimed | |
Have an agent create, update, and activate a workflow programmatically through the public API C Agent integration | ai-native user | Ai workflows — AI in the engine loop — agent-driven editors, copilots, codegen-friendly APIs, runtime inferenceAi workflows | 2 | partial | 4/10 | Tprobed | |
Map and transform data between steps with expressions, functions, or formulas C Data mapping | ops user | Code extensibility — stories about code extensibility in this arenaCode extensibility | 2 | disputed | 4/10 | Dcontradicted | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | partial | 4/10 | Cclaimed | |
Branch a workflow with conditions, filters, and parallel paths that merge back together C Builder | ops user | Visual builder — stories about visual builder in this arenaVisual builder | 2 | partialfree | 3/10 | Xcommunity | |
Inspect past execution logs and re-run a failed execution, resuming from the failing step C Observability | ops user | Reliability errors — stories about reliability errors in this arenaReliability errors | 2 | none | 0/10 | ||
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | 0/10 | ||
Run long-lived workflows that wait for days and survive worker or platform restarts without losing state C Durability | developer | Reliability errors — stories about reliability errors in this arenaReliability errors | 2 | none | 0/10 | ||
Run workflows locally or against a dev instance for development and CI testing C Local dev | developer | Deployment embedding — stories about deployment embedding in this arenaDeployment embedding | 2 | none | 0/10 | ||
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Compose reusable sub-workflows or modules that other workflows call C Composition | developer | Visual builder — stories about visual builder in this arenaVisual builder | 2 | none | untested | none yet | |
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Pause a workflow to wait for human approval or input before it continues C Human in the loop | ops user | Collaboration governance — stories about collaboration governance in this arenaCollaboration governance | 2 | none | untested | none yet | |
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | none | untested | none yet | |
Run workflows on cron-style schedules with timezone control C Schedules | ops user | Triggers scheduling — stories about triggers scheduling in this arenaTriggers scheduling | 2 | none | untested | none yet | |
Start from a public library of workflow templates instead of building from scratch C Templates | ops user | Connectors ecosystem — stories about connectors ecosystem in this arenaConnectors ecosystem | 2 | none | untested | none yet | |
Test a workflow with sample or pinned data and inspect each step's input and output before going live C Testing | developer | Visual builder — stories about visual builder in this arenaVisual builder | 2 | none | untested | none yet | |
Version workflows through source control or environments and promote changes from dev to production C Versioning | developer | Collaboration governance — stories about collaboration governance in this arenaCollaboration governance | 2 | none | untested | none yet | |
Embed the automation platform white-label inside my own product for my customers C Embedding | developer | Deployment embedding — stories about deployment embedding in this arenaDeployment embedding | 1 | full | 7/10 | Cclaimed | |
Install community-built nodes, components, or integrations contributed outside the vendor C Community | developer | Connectors ecosystem — stories about connectors ecosystem in this arenaConnectors ecosystem | 1 | partial | 5/10 | Cclaimed | |
Throttle or queue workflow executions to respect downstream rate limits C Durability | developer | Reliability errors — stories about reliability errors in this arenaReliability errors | 1 | none | untested | none yet | |
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | none | untested | none yet |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 41 stories with headroom
What would move Zapier’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools
nonemoves agent-readyimpact 45
All evidence describes Zapier acting as an MCP *server* (zapier.com/mcp) that other AI clients (Claude, ChatGPT, Cursor) connect to in order to use Zapier's own tools — not Zapier acting as an MCP *client* that ingests external MCP servers so Zapier itself can call their tools.
Reliability errors — stories about reliability errors in this arenaConfigure automatic retries with backoff for failed steps or activities
nonemoves PA Scoreimpact 30
No evidence in the pack mentions retry policies, backoff configuration, or error-handling settings for failed Zap steps or actions; the only related item is generic AI-generated troubleshooting instructions, which is not the same as configurable retry/backoff.
Code extensibility — stories about code extensibility in this arenaDrop into real code (JavaScript or Python) as a step inside a workflow
nonemoves PA Scoreimpact 30
The evidence pack never documents a native 'Code by Zapier' step allowing inline JavaScript/Python inside a Zap; the closest content is about the CLI for building whole integrations (zapier-docs-3, zapier-docs-19), not an in-workflow code step.
Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave
nonemoves PA Scoreimpact 30
No evidence of any data export feature (e.g., exporting Zaps, workflow configs, or automation history in open/portable formats) that would let a user leave the platform with their data intact; evidence focuses on integrations, MCP, and building automations, not on data portability/export.
Openness — open source, data portability, and self-hosting storiesSelf-host the core product
nonemoves PA Scoreimpact 30
The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na".
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
No evidence pack item addresses AI training data usage, opt-out controls, or data privacy policies regarding model training; only SOC 2 certification is mentioned in passing without connection to training data opt-out.
Agenticness — how well agents can access and operate the productExplore an interactive API reference with runnable examples
nonemoves API qualityimpact 30
Zapier has developer docs, CLI docs, and a Workflow API, so an interactive API reference is a fair axis to expect, but the evidence pack shows no such feature—probes explicitly found no OpenAPI/swagger spec (404s across all candidate paths) and no mention of a runnable/interactive API console anywhere in the docs.
Agenticness — how well agents can access and operate the productDownload a machine-readable API spec (OpenAPI or equivalent)
nonemoves API qualityimpact 30
Missing: a publicly downloadable OpenAPI/Swagger JSON or YAML file, any documentation page linking to such a spec.
Showing the top 8 of 41 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map11 surfaces · 30 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
Integrations docs14 stories
- Run the product headlessly / in CI for automation
- Use an official CLI
- Drive the product through a documented public API
- Build against official SDKs
- Subscribe to events via webhooks
- Schedule recurring jobs or workflows
- Build a custom connector or private integration with a documented developer platform, SDK, or CLI
- Map and transform data between steps with expressions, functions, or formulas
- Install community-built nodes, components, or integrations contributed outside the vendor
- Do everything through the API that I can do in the UI
- Trigger workflows from events in connected apps (new record, message, email, form submission)
- Expose a custom webhook URL that receives external HTTP requests and starts a workflow run with the payload
- Branch a workflow with conditions, filters, and parallel paths that merge back together
- Build multi-step workflows in a visual editor without writing code
docs.zapier.com12 stories
- Point an agent at llms.txt or agent-oriented docs
- Connect an agent via an official MCP server
- Use an official CLI
- Issue scoped/least-privilege API credentials for an agent
- Build against official SDKs
- Expose my workflows or connected app actions as MCP tools that an external agent can call
- Define rules that trigger actions automatically on events
- Build a custom connector or private integration with a documented developer platform, SDK, or CLI
- Store connection credentials centrally, share them with my team, and control who can use which credential
- Install community-built nodes, components, or integrations contributed outside the vendor
- Connect to thousands of apps through prebuilt, vendor-maintained integrations
- Embed the automation platform white-label inside my own product for my customers
MCP docs11 stories
- Connect an agent via an official MCP server
- Issue scoped/least-privilege API credentials for an agent
- Set up automations that run autonomously in the background
- Operate the product with natural-language commands
- Have an agent create, update, and activate a workflow programmatically through the public API
- Expose my workflows or connected app actions as MCP tools that an external agent can call
- Add AI agent or LLM steps inside a workflow, with model choice and tool use
- Define rules that trigger actions automatically on events
- Schedule recurring jobs or workflows
- Connect to thousands of apps through prebuilt, vendor-maintained integrations
- Do everything through the API that I can do in the UI
MCP docs9 stories
- Connect an agent via an official MCP server
- Issue scoped/least-privilege API credentials for an agent
- Set up automations that run autonomously in the background
- Operate the product with natural-language commands
- Expose my workflows or connected app actions as MCP tools that an external agent can call
- Generate or edit a workflow from a natural-language prompt
- Schedule recurring jobs or workflows
- Store connection credentials centrally, share them with my team, and control who can use which credential
- Connect to thousands of apps through prebuilt, vendor-maintained integrations
Hacker News8 stories
- Set up automations that run autonomously in the background
- Define rules that trigger actions automatically on events
- Map and transform data between steps with expressions, functions, or formulas
- Connect to thousands of apps through prebuilt, vendor-maintained integrations
- Trigger workflows from events in connected apps (new record, message, email, form submission)
- Expose a custom webhook URL that receives external HTTP requests and starts a workflow run with the payload
- Branch a workflow with conditions, filters, and parallel paths that merge back together
- Build multi-step workflows in a visual editor without writing code
Developer platform docs7 stories
- Run the product headlessly / in CI for automation
- Drive the product through a documented public API
- Subscribe to events via webhooks
- Have an agent create, update, and activate a workflow programmatically through the public API
- Build a custom connector or private integration with a documented developer platform, SDK, or CLI
- Embed the automation platform white-label inside my own product for my customers
- Do everything through the API that I can do in the UI
Hc docs6 stories
- Get AI-generated insights and suggestions from my data inside the product
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- Generate or edit a workflow from a natural-language prompt
- Add AI agent or LLM steps inside a workflow, with model choice and tool use
- Define dedicated error-handling paths or error workflows and get notified when a run fails
Agents docs5 stories
- Get AI-generated insights and suggestions from my data inside the product
- Set up automations that run autonomously in the background
- Delegate tasks to a built-in AI assistant inside the product
- Generate or edit a workflow from a natural-language prompt
- Add AI agent or LLM steps inside a workflow, with model choice and tool use
Canvas docs5 stories
- Get AI-generated insights and suggestions from my data inside the product
- Delegate tasks to a built-in AI assistant inside the product
- Define rules that trigger actions automatically on events
- Map and transform data between steps with expressions, functions, or formulas
- Trigger workflows from events in connected apps (new record, message, email, form submission)
OpenAPI spec4 stories
Probe proofs — replayable recordings from the probe harnessProbe proofs
Replayable recordings from our probe harness — see the Prove-It protocol to submit one.
$zapier-platform --versionreproduced$ zapier-platform --version * CLI version: 19.1.0 * Node.js version: v26.0.0 * OS info: darwin-arm64
$curl -si -X POST https://mcp.zapier.com/api/mcp/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'reproduced$ curl -si -X POST https://mcp.zapier.com/api/mcp/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'
HTTP/2 401
content-type: application/json; charset=utf-8
content-length: 108
vary: Origin, Accept-Encoding
access-control-allow-credentials: true
www-authenticate: Bearer realm="Zapier MCP", error="invalid_[redacted]"
date: Sat, 05 Sep 2026 00:25:21 GMT
strict-transport-security: max-age=31536000;includeSubdomains;preload
x-cache: Error from cloudfront
via: 1.1 188e78960502f402bcdf825ba82688e2.cloudfront.net (CloudFront)
x-amz-cf-pop: SFO53-P4
x-amz-cf-id: 8NeF3EC-YuhGcHkGbQnCU2Hx20vF_dAJ5I1WzAMXztuPoaBE8UHcqQ==
{"jsonrpc":"2.0","id":null,"error":{"code":-31996,"message":"Expected Bearer [redacted] for MCP authentication"}}
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
8 of 13 testable claims verified · 0 contradicted → integrity 62/100
19 distinct capability claims found in Zapier’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
8
Verified
5
Unverified
0
Contradicted
16
Undersold
Verified (18)
“Provides a platform for vendors to design triggers/actions, wire authentication, and publish an integration to the Zapier App Directory”
Build a custom connector or private integration with a documented developer platform, SDK, or CLIfullproof ↗
“Gives coding agents programmatic, token-free access to 9,000+ apps by handling OAuth and credential complexity”
Drive the product through a documented public APIpartialproof ↗
“Platform CLI lets developers build integrations with Node.js, OAuth1/2, webhooks, polling triggers, and HTTP middleware”
Build a custom connector or private integration with a documented developer platform, SDK, or CLIfullproof ↗
“Platform CLI lets developers build integrations with Node.js, OAuth1/2, webhooks, polling triggers, and HTTP middleware”
“Agent skills built on Zapier can be discovered on npm/skill registries and run as an agent skill, CLI, typed Node module, or local MCP server”
“Agent skills built on Zapier can be discovered on npm/skill registries and run as an agent skill, CLI, typed Node module, or local MCP server”
“Agent skills built on Zapier can be discovered on npm/skill registries and run as an agent skill, CLI, typed Node module, or local MCP server”
“AI tools like Claude, ChatGPT, and Cursor can connect to Gmail, Slack, Salesforce, and 9,000+ apps with no code required”
“A single natural-language prompt can have an AI find availability and book a meeting across calendars”
Operate the product with natural-language commandsfullproof ↗
“Visual mapping tool (Canvas) lets teams add owners, notes, and images to build structured, documented process diagrams”
Build multi-step workflows in a visual editor without writing codefullproof ↗
“Any MCP-compatible AI client can get one governed, SOC 2-certified connection to 9,000+ apps with no code or infrastructure required”
“Canvas automatically maps and optimizes business processes to help teams document, refine, and automate them”
Build multi-step workflows in a visual editor without writing codefullproof ↗
“Users can build workflows either with a no-code Visual Builder for quick setups or with the CLI for full developer control”
Build multi-step workflows in a visual editor without writing codefullproof ↗
“Users can build workflows either with a no-code Visual Builder for quick setups or with the CLI for full developer control”
Build a custom connector or private integration with a documented developer platform, SDK, or CLIfullproof ↗
“Users can describe a task in plain language and the AI calls the correct Zapier action and confirms what it did”
Operate the product with natural-language commandsfullproof ↗
“The Visual Builder enables quick deployment and cross-team collaboration on automations without developer expertise”
Build multi-step workflows in a visual editor without writing codefullproof ↗
“A Workflow API combined with 9,000+ integrations can power a custom built-in automation experience, integration marketplace, or AI workflows”
Drive the product through a documented public APIpartialproof ↗
“AI agents can take real actions like sending messages, creating tasks, and updating records across 9,000+ apps and 40,000+ actions”
Connect to thousands of apps through prebuilt, vendor-maintained integrationsfullproof ↗
Unverified (6)
“Automation capabilities can be embedded directly into another product so end users connect apps and run automations under that product's own brand”
Embed the automation platform white-label inside my own product for my customersfullproof ↗
“Users can create specialized AI agents, assisted by Zapier Copilot, that connect to business data and perform tasks across 9,000+ apps”
Delegate tasks to a built-in AI assistant inside the productpartialproof ↗
“Zapier uses AI to generate troubleshooting instructions for users to review”
Get AI-generated insights and suggestions from my data inside the productpartialproof ↗
“Existing app connections/credentials set up in a Zapier account are automatically reused rather than requiring re-authentication”
Store connection credentials centrally, share them with my team, and control who can use which credentialpartialproof ↗
“IT can manage one governed MCP connection with account-level restrictions and workspace controls that apply across every AI agent (Claude, ChatGPT, Cursor)”
Issue scoped/least-privilege API credentials for an agentpartialproof ↗
“A Workflow API combined with 9,000+ integrations can power a custom built-in automation experience, integration marketplace, or AI workflows”
Embed the automation platform white-label inside my own product for my customersfullproof ↗
Undersold (16)
Point an agent at llms.txt or agent-oriented docsfullproof ↗
Run the product headlessly / in CI for automationpartialproof ↗
Set up automations that run autonomously in the backgroundfullproof ↗
Have an agent create, update, and activate a workflow programmatically through the public APIpartialproof ↗
Expose my workflows or connected app actions as MCP tools that an external agent can callfullproof ↗
Generate or edit a workflow from a natural-language promptpartialproof ↗
Add AI agent or LLM steps inside a workflow, with model choice and tool usepartialproof ↗
Define rules that trigger actions automatically on eventsfullproof ↗
Install community-built nodes, components, or integrations contributed outside the vendorpartialproof ↗
Do everything through the API that I can do in the UIpartialproof ↗
Define dedicated error-handling paths or error workflows and get notified when a run failspartialproof ↗
Trigger workflows from events in connected apps (new record, message, email, form submission)fullproof ↗
Expose a custom webhook URL that receives external HTTP requests and starts a workflow run with the payloadfullproof ↗
Branch a workflow with conditions, filters, and parallel paths that merge back togetherpartialproof ↗
Business model
Free tier with limited Zaps and tasks; paid plans are flat monthly fees metered by task volume, with add-on pricing for Tables/Interfaces/Agents and custom enterprise contracts.
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Try Experimental
Run it in the microterminal →Recorded agent sessions — and a live MCP handshake where the vendor ships one.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents
Agent surface uptime MCP 100% · llms.txt 100% (30d, checked every 6h since Sep 8 '26)