{
  "doc": {
    "id": "cloud/features/cypress-ai-features",
    "title": "AI features in Cypress",
    "description": "Learn about AI-powered testing capabilities and tools in Cypress — including cy.prompt(), Studio AI, and Cloud AI features for test generation, self-healing, and failure analysis.",
    "section": "cloud",
    "source_path": "/llm/markdown/cloud/features/cypress-ai-features.md",
    "version": "e6c8d867c21227247f14714fb5690c7c018983c5",
    "updated_at": "2026-08-08T12:39:37.868Z",
    "headings": [
      {
        "id": "cloud/features/cypress-ai-features#cypress-ai",
        "text": "Cypress AI",
        "level": 1
      },
      {
        "id": "cloud/features/cypress-ai-features#the-problem-developers-face",
        "text": "The Problem Developers Face",
        "level": 2
      },
      {
        "id": "cloud/features/cypress-ai-features#getting-started",
        "text": "Getting Started",
        "level": 2
      },
      {
        "id": "cloud/features/cypress-ai-features#how-cypress-ai-fits-into-the-workflow",
        "text": "How Cypress AI Fits Into the Workflow",
        "level": 2
      },
      {
        "id": "cloud/features/cypress-ai-features#ai-capabilities",
        "text": "AI Capabilities",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#ai-tools",
        "text": "AI Tools",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#capabilities-in-detail",
        "text": "Capabilities in detail",
        "level": 2
      },
      {
        "id": "cloud/features/cypress-ai-features#cy-prompt",
        "text": "cy.prompt()",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#workflow-1-generate-once-commit-to-source-control",
        "text": "Workflow 1: Generate once, commit to source control",
        "level": 4
      },
      {
        "id": "cloud/features/cypress-ai-features#workflow-2-continuous-self-healing",
        "text": "Workflow 2: Continuous self-healing",
        "level": 4
      },
      {
        "id": "cloud/features/cypress-ai-features#studio-ai",
        "text": "Studio AI",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#test-intent-summaries",
        "text": "Test Intent Summaries",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#error-summaries",
        "text": "Error Summaries",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#ui-coverage-test-generation",
        "text": "UI Coverage Test Generation",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#ai-tools-in-detail",
        "text": "AI Tools in detail",
        "level": 2
      },
      {
        "id": "cloud/features/cypress-ai-features#ai-skills",
        "text": "AI Skills",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#cloud-mcp",
        "text": "Cloud MCP",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#cloud-cli",
        "text": "Cloud CLI",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#faqs",
        "text": "FAQs",
        "level": 2
      },
      {
        "id": "cloud/features/cypress-ai-features#why-do-i-need-a-cloud-account",
        "text": "Why do I need a Cloud Account?",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#usage-limits",
        "text": "Usage limits",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#pricing",
        "text": "Pricing",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#release-status",
        "text": "Release Status",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#security-and-data-handling",
        "text": "Security and data handling",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#disabling-ai-features",
        "text": "Disabling AI features",
        "level": 3
      },
      {
        "id": "cloud/features/cypress-ai-features#see-also",
        "text": "See also",
        "level": 2
      }
    ]
  },
  "chunks": [
    {
      "id": "cloud/features/cypress-ai-features#the-problem-developers-face",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "The Problem Developers Face",
      "heading_level": 2,
      "content_markdown": "## The Problem Developers Face\n\nWriting tests, maintaining them, and debugging failures is time-consuming and repetitive:\n\n*   Writing tests requires boilerplate and memorizing commands.\n*   Understanding large test suites is hard for new team members.\n*   Debugging failures often means staring at logs and replaying tests.\n*   Identifying missing coverage is manual and error-prone.\n\nCypress AI is designed to solve these problems without changing how you already work.\n",
      "section": "cloud",
      "anchors": [
        "the-problem-developers-face"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 91
    },
    {
      "id": "cloud/features/cypress-ai-features#getting-started",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Getting Started",
      "heading_level": 2,
      "content_markdown": "## Getting Started\n\nAI Capabilities are enabled by default for all users in your organization on an applicable plan. Login to your Cypress Cloud account to get started.\n\nEach AI Tool must be enabled and installed individually. See each tool's documentation for instructions.\n",
      "section": "cloud",
      "anchors": [
        "getting-started"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 57
    },
    {
      "id": "cloud/features/cypress-ai-features#how-cypress-ai-fits-into-the-workflow",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "How Cypress AI Fits Into the Workflow",
      "heading_level": 2,
      "content_markdown": "## How Cypress AI Fits Into the Workflow\n\nCypress AI are easy-to-use capabilities and tools across your testing lifecycle. They are woven into the core workflow.\n\n### AI Capabilities\n\n| When To Use | AI Capability | Outcome |\n| --- | --- | --- |\n| Author Tests | cy.prompt(), Studio AI | Generate commands, assertions, and full tests from natural language or UI exploration |\n| Understand Tests | Test Intent Summaries | Quickly see what tests verify, reducing cognitive load and onboarding friction |\n| Debug Failures | Error Summaries | AI-powered explanations for what happened when a test failed |\n| Test maintenance | cy.prompt() | Automatically adapt to UI changes that would otherwise break selectors |\n| Fill Coverage Gaps | UI Coverage Test Generation | Identify untested flows and automatically generate new tests |\n\n### AI Tools\n\n| When To Use | AI Tool | Outcome |\n| --- | --- | --- |\n| Author Tests | `cypress-author` and `cypress-docs` Skills | Improves how AI tools create, update, and fix Cypress tests. |\n| Understand Tests | `cypress-explain` Skill | Helps AI describe, and critique existing tests. |\n| Analyze & Triage | Cloud MCP | Gives AI coding assistants and AI agents a direct window into your application's health and stability |\n| Triage & Automate | Cloud CLI | Brings Cloud data and Test Replay access to the terminal for triage, scripting, CI, and terminal-based AI agents |\n",
      "section": "cloud",
      "anchors": [
        "how-cypress-ai-fits-into-the-workflow"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 329
    },
    {
      "id": "cloud/features/cypress-ai-features#ai-capabilities",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "AI Capabilities",
      "heading_level": 3,
      "content_markdown": "### AI Capabilities\n\n| When To Use | AI Capability | Outcome |\n| --- | --- | --- |\n| Author Tests | cy.prompt(), Studio AI | Generate commands, assertions, and full tests from natural language or UI exploration |\n| Understand Tests | Test Intent Summaries | Quickly see what tests verify, reducing cognitive load and onboarding friction |\n| Debug Failures | Error Summaries | AI-powered explanations for what happened when a test failed |\n| Test maintenance | cy.prompt() | Automatically adapt to UI changes that would otherwise break selectors |\n| Fill Coverage Gaps | UI Coverage Test Generation | Identify untested flows and automatically generate new tests |\n",
      "section": "cloud",
      "anchors": [
        "ai-capabilities"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 152
    },
    {
      "id": "cloud/features/cypress-ai-features#ai-tools",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "AI Tools",
      "heading_level": 3,
      "content_markdown": "### AI Tools\n\n| When To Use | AI Tool | Outcome |\n| --- | --- | --- |\n| Author Tests | `cypress-author` and `cypress-docs` Skills | Improves how AI tools create, update, and fix Cypress tests. |\n| Understand Tests | `cypress-explain` Skill | Helps AI describe, and critique existing tests. |\n| Analyze & Triage | Cloud MCP | Gives AI coding assistants and AI agents a direct window into your application's health and stability |\n| Triage & Automate | Cloud CLI | Brings Cloud data and Test Replay access to the terminal for triage, scripting, CI, and terminal-based AI agents |\n",
      "section": "cloud",
      "anchors": [
        "ai-tools"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 143
    },
    {
      "id": "cloud/features/cypress-ai-features#capabilities-in-detail",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Capabilities in detail",
      "heading_level": 2,
      "content_markdown": "## Capabilities in detail\n\n### cy.prompt()\n\n**Best for:** teams who want to generate Cypress test code from plain English, or reduce selector maintenance as their UI evolves.\n\n`cy.prompt()` is a Cypress command that converts natural language test steps into executable Cypress commands. It uses AI to interpret each step, evaluate the DOM, generate selectors, and produce Cypress code. `cy.prompt()` supports two workflows.\n\n```\ncy.prompt(  [    'visit https://cloud.cypress.io/login',    'type \"user@example.com\" in the email field',    'type {{password}} in the password field',    'click the login button',    'verify we are redirected to the dashboard',  ],  {    placeholders: { password: 'secret123' },  })\n```\n\n#### Workflow 1: Generate once, commit to source control\n\nUse `cy.prompt()` to generate a test quickly, then export and commit the generated code.\n\nThis workflow is a good fit when:\n\n*   Your app has stable, predictable elements.\n*   You want predictable, reviewable test code in version control.\n*   You want to use AI to accelerate authoring but prefer to own the output.\n\n#### Workflow 2: Continuous self-healing\n\nKeep `cy.prompt()` running in your tests. When a selector fails between runs, Cypress regenerates code for that step automatically. This is \"self-healing\" — the test adapts without manual intervention.\n\nThis workflow is a good fit when:\n\n*   Your app is in active development and UI changes frequently.\n*   You are willing to accept AI calls at runtime in exchange for less maintenance.\n*   You understand that self-healing works best when it catches occasional, unexpected changes — not when selectors change on every run.\n\n[Read the full cy.prompt() documentation →](/llm/markdown/api/commands/prompt.md)\n\n### Studio AI\n\n**Best for:** teams who want to write assertions faster without guessing what to assert after every interaction.\n\n[Cypress Studio](/llm/markdown/app/guides/cypress-studio.md) lets you build and extend E2E tests by recording real interactions in your app. Studio AI adds assertion recommendations on top: as you record, it watches what changes in the UI and suggests assertions automatically. You review them, keep what fits, and save.\n\nStudio AI observes DOM changes between interactions and generates assertions based on what actually changed — visibility, text content, form values, element attributes, URL changes, and more. It does not have access to your application's source code or business logic.\n\n[Read the full Studio AI documentation →](/llm/markdown/app/guides/cypress-studio.md)\n\n### Test Intent Summaries\n\n**Best for:** teams who need to understand what a test is checking without reading every command or watching a full Test Replay.\n\nTest Intent Summaries are AI-generated descriptions of a test's purpose, available in the Cypress Cloud test details sidebar. They help you orient quickly — whether you are reviewing a new test or debugging a failure — without needing to trace through the command log manually.\n\nTest Intent Summaries are available on all Cypress Cloud plans at no additional cost.\n\n### Error Summaries\n\n**Best for:** teams who want to understand why a test failed without parsing raw stack traces.\n\n\"At a glance\" Error Summaries are plain-language explanations of what went wrong in a failed test attempt, available alongside stack traces and error messages in the Cypress Cloud test details sidebar. They describe what led to the failure so you can jump directly to investigating the root cause.\n\nError Summaries are available on all Cypress Cloud plans at no additional cost.\n\n### UI Coverage Test Generation\n\n**Best for:** teams using UI Coverage who want to close coverage gaps without writing tests from scratch.\n\nUI Coverage Test Generation lets you generate targeted Cypress tests directly from coverage gaps identified during code reviews. Instead of manually identifying what to test, you can generate a test scaffold from the gap and refine from there.\n\nThis capability is included with UI Coverage and is not available on standard Cloud plans.\n\n[Read the UI Coverage Test Generation documentation →](/llm/markdown/ui-coverage/guides/address-coverage-gaps.md#Generate-tests-from-UI-Coverage-reports)\n",
      "section": "cloud",
      "anchors": [
        "capabilities-in-detail"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 820
    },
    {
      "id": "cloud/features/cypress-ai-features#cy-prompt",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "cy.prompt()",
      "heading_level": 3,
      "content_markdown": "### cy.prompt()\n\n**Best for:** teams who want to generate Cypress test code from plain English, or reduce selector maintenance as their UI evolves.\n\n`cy.prompt()` is a Cypress command that converts natural language test steps into executable Cypress commands. It uses AI to interpret each step, evaluate the DOM, generate selectors, and produce Cypress code. `cy.prompt()` supports two workflows.\n\n```\ncy.prompt(  [    'visit https://cloud.cypress.io/login',    'type \"user@example.com\" in the email field',    'type {{password}} in the password field',    'click the login button',    'verify we are redirected to the dashboard',  ],  {    placeholders: { password: 'secret123' },  })\n```\n\n#### Workflow 1: Generate once, commit to source control\n\nUse `cy.prompt()` to generate a test quickly, then export and commit the generated code.\n\nThis workflow is a good fit when:\n\n*   Your app has stable, predictable elements.\n*   You want predictable, reviewable test code in version control.\n*   You want to use AI to accelerate authoring but prefer to own the output.\n\n#### Workflow 2: Continuous self-healing\n\nKeep `cy.prompt()` running in your tests. When a selector fails between runs, Cypress regenerates code for that step automatically. This is \"self-healing\" — the test adapts without manual intervention.\n\nThis workflow is a good fit when:\n\n*   Your app is in active development and UI changes frequently.\n*   You are willing to accept AI calls at runtime in exchange for less maintenance.\n*   You understand that self-healing works best when it catches occasional, unexpected changes — not when selectors change on every run.\n\n[Read the full cy.prompt() documentation →](/llm/markdown/api/commands/prompt.md)\n",
      "section": "cloud",
      "anchors": [
        "cy-prompt"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 335
    },
    {
      "id": "cloud/features/cypress-ai-features#workflow-1-generate-once-commit-to-source-control",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Workflow 1: Generate once, commit to source control",
      "heading_level": 4,
      "content_markdown": "#### Workflow 1: Generate once, commit to source control\n\nUse `cy.prompt()` to generate a test quickly, then export and commit the generated code.\n\nThis workflow is a good fit when:\n\n*   Your app has stable, predictable elements.\n*   You want predictable, reviewable test code in version control.\n*   You want to use AI to accelerate authoring but prefer to own the output.\n",
      "section": "cloud",
      "anchors": [
        "workflow-1-generate-once-commit-to-source-control"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 83
    },
    {
      "id": "cloud/features/cypress-ai-features#workflow-2-continuous-self-healing",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Workflow 2: Continuous self-healing",
      "heading_level": 4,
      "content_markdown": "#### Workflow 2: Continuous self-healing\n\nKeep `cy.prompt()` running in your tests. When a selector fails between runs, Cypress regenerates code for that step automatically. This is \"self-healing\" — the test adapts without manual intervention.\n\nThis workflow is a good fit when:\n\n*   Your app is in active development and UI changes frequently.\n*   You are willing to accept AI calls at runtime in exchange for less maintenance.\n*   You understand that self-healing works best when it catches occasional, unexpected changes — not when selectors change on every run.\n\n[Read the full cy.prompt() documentation →](/llm/markdown/api/commands/prompt.md)\n",
      "section": "cloud",
      "anchors": [
        "workflow-2-continuous-self-healing"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 125
    },
    {
      "id": "cloud/features/cypress-ai-features#studio-ai",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Studio AI",
      "heading_level": 3,
      "content_markdown": "### Studio AI\n\n**Best for:** teams who want to write assertions faster without guessing what to assert after every interaction.\n\n[Cypress Studio](/llm/markdown/app/guides/cypress-studio.md) lets you build and extend E2E tests by recording real interactions in your app. Studio AI adds assertion recommendations on top: as you record, it watches what changes in the UI and suggests assertions automatically. You review them, keep what fits, and save.\n\nStudio AI observes DOM changes between interactions and generates assertions based on what actually changed — visibility, text content, form values, element attributes, URL changes, and more. It does not have access to your application's source code or business logic.\n\n[Read the full Studio AI documentation →](/llm/markdown/app/guides/cypress-studio.md)\n",
      "section": "cloud",
      "anchors": [
        "studio-ai"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 149
    },
    {
      "id": "cloud/features/cypress-ai-features#test-intent-summaries",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Test Intent Summaries",
      "heading_level": 3,
      "content_markdown": "### Test Intent Summaries\n\n**Best for:** teams who need to understand what a test is checking without reading every command or watching a full Test Replay.\n\nTest Intent Summaries are AI-generated descriptions of a test's purpose, available in the Cypress Cloud test details sidebar. They help you orient quickly — whether you are reviewing a new test or debugging a failure — without needing to trace through the command log manually.\n\nTest Intent Summaries are available on all Cypress Cloud plans at no additional cost.\n",
      "section": "cloud",
      "anchors": [
        "test-intent-summaries"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 113
    },
    {
      "id": "cloud/features/cypress-ai-features#error-summaries",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Error Summaries",
      "heading_level": 3,
      "content_markdown": "### Error Summaries\n\n**Best for:** teams who want to understand why a test failed without parsing raw stack traces.\n\n\"At a glance\" Error Summaries are plain-language explanations of what went wrong in a failed test attempt, available alongside stack traces and error messages in the Cypress Cloud test details sidebar. They describe what led to the failure so you can jump directly to investigating the root cause.\n\nError Summaries are available on all Cypress Cloud plans at no additional cost.\n",
      "section": "cloud",
      "anchors": [
        "error-summaries"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 107
    },
    {
      "id": "cloud/features/cypress-ai-features#ui-coverage-test-generation",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "UI Coverage Test Generation",
      "heading_level": 3,
      "content_markdown": "### UI Coverage Test Generation\n\n**Best for:** teams using UI Coverage who want to close coverage gaps without writing tests from scratch.\n\nUI Coverage Test Generation lets you generate targeted Cypress tests directly from coverage gaps identified during code reviews. Instead of manually identifying what to test, you can generate a test scaffold from the gap and refine from there.\n\nThis capability is included with UI Coverage and is not available on standard Cloud plans.\n\n[Read the UI Coverage Test Generation documentation →](/llm/markdown/ui-coverage/guides/address-coverage-gaps.md#Generate-tests-from-UI-Coverage-reports)\n",
      "section": "cloud",
      "anchors": [
        "ui-coverage-test-generation"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 111
    },
    {
      "id": "cloud/features/cypress-ai-features#ai-tools-in-detail",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "AI Tools in detail",
      "heading_level": 2,
      "content_markdown": "## AI Tools in detail\n\n### AI Skills\n\n**Best for:** teams wanting to providing instructions to improve the output of AI when working with Cypress.\n\nUse skills when you want your AI tool to:\n\n*   Apply Cypress best practices to generated and reviewed tests\n*   Steer away from brittle patterns and weak selectors\n*   Produce more Cypress-focused explanations and critiques\n*   Establish consistent AI behavior across your team and workflows\n\n[Read the AI Skills documentation →](/llm/markdown/app/tooling/ai-skills.md)\n\n### Cloud MCP\n\n**Best for:** teams moving toward agentic workflows who want to eliminate the context gap between their CI environment and their development tools.\n\nCloud MCP is a remote server that gives AI assistants a direct window into your application's health and stability. By connecting your AI coding assistant or AI agent directly to your CI results, it transforms Cypress from a testing tool into a real-time engineering data source—removing the manual overhead that makes testing a bottleneck.\n\nSince May 20, 2026, Cloud MCP has been generally available on all Cypress Cloud plans at no additional cost.\n\nInstead of spending time investigating runs, your assistant uses the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) to independently monitor and analyze recorded run data, including errors, stack traces, Test Replay links, accessibility violations, and UI Coverage gaps. This makes it easier to reach for Cypress as your tool of choice.\n\nRead the [Cloud MCP documentation →](/llm/markdown/cloud/integrations/cloud-mcp.md)\n\n### Cloud CLI\n\n**Best for:** developers and terminal-based agents that query Cloud data from scripts, CI, and the command line.\n\nThe Cloud CLI (`cy-cloud`) brings your Cypress Cloud data to the command line. Check run status, read failing tests, and pull the Test Replay timeline of commands, network requests, and console logs, all as JSON that scripts and AI agents can parse.\n\nWhere Cloud MCP connects an AI client directly to your Cloud data, the Cloud CLI is the scriptable counterpart: give it to agents that work through a terminal, or wire it into your own automation and tooling. It is available on all Cypress Cloud plans at no additional cost.\n\nRead the [Cloud CLI documentation →](/llm/markdown/cloud/integrations/cloud-cli.md)\n",
      "section": "cloud",
      "anchors": [
        "ai-tools-in-detail"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 460
    },
    {
      "id": "cloud/features/cypress-ai-features#ai-skills",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "AI Skills",
      "heading_level": 3,
      "content_markdown": "### AI Skills\n\n**Best for:** teams wanting to providing instructions to improve the output of AI when working with Cypress.\n\nUse skills when you want your AI tool to:\n\n*   Apply Cypress best practices to generated and reviewed tests\n*   Steer away from brittle patterns and weak selectors\n*   Produce more Cypress-focused explanations and critiques\n*   Establish consistent AI behavior across your team and workflows\n\n[Read the AI Skills documentation →](/llm/markdown/app/tooling/ai-skills.md)\n",
      "section": "cloud",
      "anchors": [
        "ai-skills"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 95
    },
    {
      "id": "cloud/features/cypress-ai-features#cloud-mcp",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Cloud MCP",
      "heading_level": 3,
      "content_markdown": "### Cloud MCP\n\n**Best for:** teams moving toward agentic workflows who want to eliminate the context gap between their CI environment and their development tools.\n\nCloud MCP is a remote server that gives AI assistants a direct window into your application's health and stability. By connecting your AI coding assistant or AI agent directly to your CI results, it transforms Cypress from a testing tool into a real-time engineering data source—removing the manual overhead that makes testing a bottleneck.\n\nSince May 20, 2026, Cloud MCP has been generally available on all Cypress Cloud plans at no additional cost.\n\nInstead of spending time investigating runs, your assistant uses the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) to independently monitor and analyze recorded run data, including errors, stack traces, Test Replay links, accessibility violations, and UI Coverage gaps. This makes it easier to reach for Cypress as your tool of choice.\n\nRead the [Cloud MCP documentation →](/llm/markdown/cloud/integrations/cloud-mcp.md)\n",
      "section": "cloud",
      "anchors": [
        "cloud-mcp"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 203
    },
    {
      "id": "cloud/features/cypress-ai-features#cloud-cli",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Cloud CLI",
      "heading_level": 3,
      "content_markdown": "### Cloud CLI\n\n**Best for:** developers and terminal-based agents that query Cloud data from scripts, CI, and the command line.\n\nThe Cloud CLI (`cy-cloud`) brings your Cypress Cloud data to the command line. Check run status, read failing tests, and pull the Test Replay timeline of commands, network requests, and console logs, all as JSON that scripts and AI agents can parse.\n\nWhere Cloud MCP connects an AI client directly to your Cloud data, the Cloud CLI is the scriptable counterpart: give it to agents that work through a terminal, or wire it into your own automation and tooling. It is available on all Cypress Cloud plans at no additional cost.\n\nRead the [Cloud CLI documentation →](/llm/markdown/cloud/integrations/cloud-cli.md)\n",
      "section": "cloud",
      "anchors": [
        "cloud-cli"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 156
    },
    {
      "id": "cloud/features/cypress-ai-features#faqs",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "FAQs",
      "heading_level": 2,
      "content_markdown": "## FAQs\n\n### Why do I need a Cloud Account?\n\nCypress AI features use large language models (LLMs) to interpret prompts, analyze DOM state, and generate test code. Cypress Cloud manages those LLM requests securely on your behalf.\n\nWithout a Cloud account, there is no secure channel through which to route those requests, no organizational controls to apply, and no way to enforce the data handling commitments Cypress makes to its customers.\n\n**A free Cypress Cloud account is enough to get started.**\n\n[Create a free account ➜](https://cloud.cypress.io/signup)\n\nFree accounts include a two-week trial of all paid features, including higher AI usage limits.\n\n### Usage limits\n\nUsage limits vary by feature and plan. For organization-level [`cy.prompt`](/llm/markdown/api/commands/prompt.md) execution limits and billing, see the [cy.prompt FAQ](/llm/markdown/cloud/faq.md#cyprompt).\n\nSome hourly limits apply to all plans. Those are as follows:\n\n| Capability / Tool | Free plan | Paid plan |\n| --- | --- | --- |\n| cy.prompt() prompts | 100 per hour, per user | 600 per hour, per user |\n| cy.prompt() steps | 500 per hour, per user | 3,000 per hour, per user |\n| Studio AI recommendations | 60 per hour, per user | 300 per hour, per user |\n| Test Intent Summaries | Included | Included |\n| Error Summaries | Included | Included |\n| AI Skills | unlimited | unlimited |\n| Cloud MCP requests | 100 per hour, per user | 100 per hour, per user |\n| Cloud CLI requests | 100 per hour, per user | 100 per hour, per user |\n| UI Coverage Test Generation | Not available | Included with UI Coverage |\n\nStudio AI can also be tried without logging in, capped at 6 accepted recommendations per browser session. See [Studio AI usage limits](/llm/markdown/app/guides/cypress-studio.md#Usage-limits) for details.\n\nIf you need to increase your limits, contact support at [support@cypress.io](mailto:support@cypress.io).\n\n### Pricing\n\nAI Skills are available to all Cypress users.\n\nCloud MCP, the Cloud CLI, Test Intent Summaries and Error Summaries are available for free to all Cypress Cloud plans, including the Starter plan.\n\nUI Coverage Test Generation is included with UI Coverage premium solutions subscriptions.\n\nStudio AI recommendations are provided at no additional charge during the beta period.\n\nFor [`cy.prompt`](/llm/markdown/api/commands/prompt.md) execution limits and billing, see the [cy.prompt FAQ](/llm/markdown/cloud/faq.md#cyprompt).\n\nPricing is subject to change. We will communicate any changes before they take effect.\n\nSee [Cypress Cloud plans](https://www.cypress.io/pricing) for full plan details.\n\n### Release Status\n\n| Capability / Tool | Release Status |\n| --- | --- |\n| cy.prompt | Generally Available |\n| Studio AI recommendations | Beta |\n| Test Intent Summaries | Generally Available |\n| Error Summaries | Generally Available |\n| AI Skills | Generally Available |\n| Cloud MCP | Generally Available |\n| Cloud CLI | Beta |\n| UI Coverage Test Generation | Generally Available |\n\n### Security and data handling\n\n[Read the Cypress AI Security page →](https://on.cypress.io/ai-security)\n\n### Disabling AI features\n\n**AI Capabilities** are enabled by default for all users in your organization on an applicable plan. Organization admins and owners can disable them from Cypress Cloud organization settings.\n\n**AI tools** must be installed individually and are not enabled by default. To stop using an AI Tool, remove it from your AI client's configuration.\n\nCloud MCP and the Cloud CLI can each be disabled for an organization from the organization's Integrations page. Disabling an integration immediately revokes access for all users in that organization, regardless of whether they authenticated via OAuth or a personal access token.\n",
      "section": "cloud",
      "anchors": [
        "faqs"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 779
    },
    {
      "id": "cloud/features/cypress-ai-features#why-do-i-need-a-cloud-account",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Why do I need a Cloud Account?",
      "heading_level": 3,
      "content_markdown": "### Why do I need a Cloud Account?\n\nCypress AI features use large language models (LLMs) to interpret prompts, analyze DOM state, and generate test code. Cypress Cloud manages those LLM requests securely on your behalf.\n\nWithout a Cloud account, there is no secure channel through which to route those requests, no organizational controls to apply, and no way to enforce the data handling commitments Cypress makes to its customers.\n\n**A free Cypress Cloud account is enough to get started.**\n\n[Create a free account ➜](https://cloud.cypress.io/signup)\n\nFree accounts include a two-week trial of all paid features, including higher AI usage limits.\n",
      "section": "cloud",
      "anchors": [
        "why-do-i-need-a-cloud-account"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 133
    },
    {
      "id": "cloud/features/cypress-ai-features#usage-limits",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Usage limits",
      "heading_level": 3,
      "content_markdown": "### Usage limits\n\nUsage limits vary by feature and plan. For organization-level [`cy.prompt`](/llm/markdown/api/commands/prompt.md) execution limits and billing, see the [cy.prompt FAQ](/llm/markdown/cloud/faq.md#cyprompt).\n\nSome hourly limits apply to all plans. Those are as follows:\n\n| Capability / Tool | Free plan | Paid plan |\n| --- | --- | --- |\n| cy.prompt() prompts | 100 per hour, per user | 600 per hour, per user |\n| cy.prompt() steps | 500 per hour, per user | 3,000 per hour, per user |\n| Studio AI recommendations | 60 per hour, per user | 300 per hour, per user |\n| Test Intent Summaries | Included | Included |\n| Error Summaries | Included | Included |\n| AI Skills | unlimited | unlimited |\n| Cloud MCP requests | 100 per hour, per user | 100 per hour, per user |\n| Cloud CLI requests | 100 per hour, per user | 100 per hour, per user |\n| UI Coverage Test Generation | Not available | Included with UI Coverage |\n\nStudio AI can also be tried without logging in, capped at 6 accepted recommendations per browser session. See [Studio AI usage limits](/llm/markdown/app/guides/cypress-studio.md#Usage-limits) for details.\n\nIf you need to increase your limits, contact support at [support@cypress.io](mailto:support@cypress.io).\n",
      "section": "cloud",
      "anchors": [
        "usage-limits"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 276
    },
    {
      "id": "cloud/features/cypress-ai-features#pricing",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Pricing",
      "heading_level": 3,
      "content_markdown": "### Pricing\n\nAI Skills are available to all Cypress users.\n\nCloud MCP, the Cloud CLI, Test Intent Summaries and Error Summaries are available for free to all Cypress Cloud plans, including the Starter plan.\n\nUI Coverage Test Generation is included with UI Coverage premium solutions subscriptions.\n\nStudio AI recommendations are provided at no additional charge during the beta period.\n\nFor [`cy.prompt`](/llm/markdown/api/commands/prompt.md) execution limits and billing, see the [cy.prompt FAQ](/llm/markdown/cloud/faq.md#cyprompt).\n\nPricing is subject to change. We will communicate any changes before they take effect.\n\nSee [Cypress Cloud plans](https://www.cypress.io/pricing) for full plan details.\n",
      "section": "cloud",
      "anchors": [
        "pricing"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 121
    },
    {
      "id": "cloud/features/cypress-ai-features#release-status",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Release Status",
      "heading_level": 3,
      "content_markdown": "### Release Status\n\n| Capability / Tool | Release Status |\n| --- | --- |\n| cy.prompt | Generally Available |\n| Studio AI recommendations | Beta |\n| Test Intent Summaries | Generally Available |\n| Error Summaries | Generally Available |\n| AI Skills | Generally Available |\n| Cloud MCP | Generally Available |\n| Cloud CLI | Beta |\n| UI Coverage Test Generation | Generally Available |\n",
      "section": "cloud",
      "anchors": [
        "release-status"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 97
    },
    {
      "id": "cloud/features/cypress-ai-features#disabling-ai-features",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "Disabling AI features",
      "heading_level": 3,
      "content_markdown": "### Disabling AI features\n\n**AI Capabilities** are enabled by default for all users in your organization on an applicable plan. Organization admins and owners can disable them from Cypress Cloud organization settings.\n\n**AI tools** must be installed individually and are not enabled by default. To stop using an AI Tool, remove it from your AI client's configuration.\n\nCloud MCP and the Cloud CLI can each be disabled for an organization from the organization's Integrations page. Disabling an integration immediately revokes access for all users in that organization, regardless of whether they authenticated via OAuth or a personal access token.\n",
      "section": "cloud",
      "anchors": [
        "disabling-ai-features"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 132
    },
    {
      "id": "cloud/features/cypress-ai-features#see-also",
      "doc_id": "cloud/features/cypress-ai-features",
      "heading": "See also",
      "heading_level": 2,
      "content_markdown": "## See also\n\n*   [cy.prompt()](/llm/markdown/api/commands/prompt.md)\n*   [Cypress Studio AI](/llm/markdown/app/guides/cypress-studio.md)\n*   [Cloud MCP](/llm/markdown/cloud/integrations/cloud-mcp.md)\n*   [Cloud CLI](/llm/markdown/cloud/integrations/cloud-cli.md)\n*   [AI Skills](/llm/markdown/app/tooling/ai-skills.md)\n*   [UI Coverage Test Generation](/llm/markdown/ui-coverage/guides/address-coverage-gaps.md#Generate-tests-from-UI-Coverage-reports)\n*   [Recorded Runs](/llm/markdown/cloud/features/recorded-runs.md)\n*   [Cypress AI Security](https://on.cypress.io/ai-security)\n",
      "section": "cloud",
      "anchors": [
        "see-also"
      ],
      "path": "/llm/json/chunked/cloud/features/cypress-ai-features.json",
      "token_estimate": 40
    }
  ]
}