Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Applitools

NPM · @APPLITOOLS/MCP · SCANNED SEP 20

The Applitools MCP server helps you create, update, and analyze visual tests using Applitools Eyes.

Available components

npm · @applitools/mcp 77
0 this week 77 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security90
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects sharp 0.34.5, reached via @applitools/core-base > @applitools/image > sharp. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 43 of 156 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency32
Schema Quality & AI Usability74
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2140 tokens (~267/item across 8 items; 7 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (43% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Applitools MCP server?

Applitools runs locally as an npm package, launched with npx -y @applitools/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @applitools/mcp

# add to Claude Code
claude mcp add applitools-applitools -- npx -y @applitools/mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "applitools-applitools": {
      "command": "npx",
      "args": [
        "-y",
        "@applitools/mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "applitools-applitools": {
      "command": "npx",
      "args": [
        "-y",
        "@applitools/mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add applitools-applitools -- npx -y @applitools/mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "applitools-applitools": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@applitools/mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add applitools-applitools --command npx --arg -y --arg @applitools/mcp
# ~/.hermes/config.yaml
mcp_servers:
  applitools-applitools:
    command: "npx"
    args: ["-y", "@applitools/mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "applitools-applitools": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@applitools/mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add applitools-applitools -t stdio -c npx -a -y @applitools/mcp
// mcp.json
{
  "mcpServers": {
    "applitools-applitools": {
      "command": "npx",
      "args": [
        "-y",
        "@applitools/mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 16 Sept 26 0
    • Stability: 0.97 → pass security
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 9 Sept 26 0
    • GHSA-rgj7-g3m4-5g8c affects this package: high ▼ security
    • Stability: 0.97 → pass security
    • Security disclosure: unverified → fail ▼ functional
  • 8 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/@applitools/mcp@0.5.4

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 2 findings
ID CVE Severity Vector Fix available
GHSA-f88m-g3jw-g9cj high yes
GHSA-rgj7-g3m4-5g8c high yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 156 packages
Packages resolved 156
Deprecated 1
Stale 42
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 7 exposed · ~2,120 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
eyes_add_checkpoints_to_test ~213

Add visual checkpoints to existing Playwright tests following best practices

NameTypeReqDescription
activeFilestring–Path to the currently active file or folder in the IDE (optional). Used to improve framework detection in Node.js monorepos by finding the nearest package.json relative to the active context.
fileContentstring–Test file content (optional if filePath provided or if IDE provides it)
filePathstring–Path to the test file that will be edited (optional if fileContent provided)
selectionobject–Selected code range from IDE (pass if provided to get better context, optional if not provided will process entire file)
workspaceRootstring–Workspace root directory (optional, defaults to current directory). If the workspace root is a Node.js monorepo (contains a package.json with a "workspaces" field), ask the user which package they wa…

No output schema declared.

No examples provided.

eyes_analyze_batch ~421

Fetch visual test results and textual diff descriptions from an Applitools Eyes batch URL. Use this tool when the user provides a batch URL from the Applitools dashboard (e.g. https://eyes.applitools.com/app/test-results/{batchId}) or a bare batch ID, and you need to analyze its visual test results without a Playwright HTML report on disk. This is the counterpart to `eyes_fetch_visual_results` for cases where: - The user is looking at results from a CI run or a previous run - There is no Playwright report available locally - The user pastes a batch URL from the Eyes dashboard The tool returns the same structured output as `eyes_fetch_visual_results`, including: - Per-test status (passed / failed / unresolved / new / aborted) - Textual diff descriptions for steps with visual differences - Aggregate summary statistics Note: Textual diff descriptions require DOM-based diff analysis on the server side. Steps without DOM capture (e.g. Figma, mobile native) may not have diff descriptions even when diffs are present.

NameTypeReqDescription
activeFilestring–Path to the currently active file or folder in the IDE (optional). Used to improve framework detection in Node.js monorepos by finding the nearest package.json relative to the active context.
batchUrlstringyesThe Applitools Eyes batch URL (e.g. https://eyes.applitools.com/app/test-results/{batchId}) or a bare batch ID.
serverUrlstring–Eyes server base URL (optional, auto-detected from batchUrl or defaults to https://eyes.applitools.com). Set this for on-premises Eyes deployments.
workspaceRootstring–Workspace root directory (optional, defaults to current directory). If the workspace root is a Node.js monorepo (contains a package.json with a "workspaces" field), ask the user which package they wa…
NameTypeReqDescription
messagestringyesHuman-readable summary of the visual test results
resultsarray–Detailed results grouped by batch
summaryobject–Aggregated statistics summarizing test results across all batches. Counts tests by their visual comparison status.

No examples provided.

eyes_fetch_visual_results ~690

Fetch current up-to-date visual test results from the Playwright HTML report and the Eyes server. IMPORTANT: - This tool reads the Playwright HTML report directly from disk. - **Do NOT copy or move the report file.** Instead, always point this tool to the actual report location using the `reportPath` argument when it's not in the default location. - For standard Playwright runs, the default report is at `playwright-report/index.html` in the workspace root. - For the Eyes example (`npx eyes-setup run-example`), the report is generated at: `<workspaceRoot>/eyes-examples/eyes-playwright-report/index.html` In that case, call the tool with: - `reportPath: "<workspaceRoot>/eyes-examples/eyes-playwright-report/index.html"` - `workspaceRoot: "<workspaceRoot>"` **CRITICAL: Do NOT run Playwright with `--reporter=list`, `--reporter=dot`, `--reporter=line`, or any other `--reporter` flag that overrides the configured reporters. Doing so suppresses the Eyes reporter, preventing it from writing results to the HTML report. This tool will then read a stale report from a previous run and return outdated results.** Always run Playwright without reporter overrides, for example: - ✅ CORRECT: `npx playwright test` - ❌ INCORRECT: `npx playwright test --reporter=list` **Stale report detection (optional):** If you know the batch IDs from the current Playwright run output, pass them via the `expectedBatchIds` parameter. This tool will warn you if those batch IDs are not found in the report, indicating the report may be from a previous run. The tool returns structured test results that can be displayed in a table, including: - Test name - Visual test status (passed/failed/unresolved/new/aborted) - Retry attempt number - Browser/device configuration [CORE REQUIREMENT: URL INTEGRITY] Visual-results URLs returned by Eyes end with `~~`. These tildes are a dashboard sentinel, not typos. You are strictly forbidden from stripping trailing tildes from these links. Render them with mar…

NameTypeReqDescription
activeFilestring–Path to the currently active file or folder in the IDE (optional). Used to improve framework detection in Node.js monorepos by finding the nearest package.json relative to the active context.
expectedBatchIdsarray–Optional list of batch IDs extracted from the Playwright run output. When provided, the tool verifies these IDs appear in the report to confirm it is current and not stale from a previous run.
reportPathstring–Path to the Playwright HTML report (optional, defaults to playwright-report/index.html)
serverUrlstring–Optional Applitools server URL (defaults to https://eyes.applitools.com)
workspaceRootstring–Workspace root directory (optional, defaults to current directory). If the workspace root is a Node.js monorepo (contains a package.json with a "workspaces" field), ask the user which package they wa…
NameTypeReqDescription
messagestringyesHuman-readable summary of the visual test results
resultsarray–Detailed results grouped by batch
summaryobject–Aggregated statistics summarizing test results across all batches. Counts tests by their visual comparison status.

No examples provided.

eyes_get_batch_url ~131

═══════════════════════════════════════ 📋 SHOW THIS MESSAGE TO USER AS-IS ═══════════════════════════════════════ Extract and convert Eyes test result URLs from console output. Parses the test execution output to find session URLs and converts them to batch URLs for viewing all test results together in the Eyes dashboard. This tool extracts URLs only - use eyes_fetch_visual_results to get detailed test status and results data.

NameTypeReqDescription
testOutputstringyesThe console output from running the Playwright test
workspaceRootstring–Workspace root directory (optional, defaults to current directory)
NameTypeReqDescription
batchUrls––Array of batch URLs for viewing all test results together in the Eyes dashboard. Null if no URLs found.
messagestringyesHuman-readable summary of URL extraction results
sessionUrls––Array of individual session URLs from test output (may end with ~~). Null if no URLs found.
testResults––Additional test result metadata if available

No examples provided.

eyes_setup_project ~250

Get step-by-step instructions to set up a Playwright JS project with Applitools Eyes (Fixtures variant) [CORE REQUIREMENT: URL INTEGRITY] Playwright visual results return URLs ending in ~~. These are not typos. You are strictly forbidden from stripping trailing tildes from these links. Use markdown [Visual Test results](URL with tildes) for links. Output the raw, verbatim URL string exactly as captured from the test output.

NameTypeReqDescription
activeFilestring–Path to the currently active file or folder in the IDE (optional). Used to improve framework detection in Node.js monorepos by finding the nearest package.json relative to the active context.
apiKeystring–Optional API key (will use validated key from session if not provided)
projectNamestring–Optional project name
workspaceRootstring–Workspace root directory (optional, defaults to current directory). If the workspace root is a Node.js monorepo (contains a package.json with a "workspaces" field), ask the user which package they wa…

No output schema declared.

No examples provided.

eyes_setup_ufg ~240

Configure Ultrafast Grid (UFG) for cross-browser and cross-device testing [CORE REQUIREMENT: URL INTEGRITY] Playwright visual results return URLs ending in ~~. These are not typos. You are strictly forbidden from stripping trailing tildes from these links. Use markdown [Visual Test results](URL with tildes) for links. Output the raw, verbatim URL string exactly as captured from the test output.

NameTypeReqDescription
activeFilestring–Path to the currently active file or folder in the IDE (optional). Used to improve framework detection in Node.js monorepos by finding the nearest package.json relative to the active context.
playwrightConfigPathstring–Path to playwright.config.js/ts file (optional, will be auto-detected)
workspaceRootstring–Workspace root directory (optional, defaults to current directory). If the workspace root is a Node.js monorepo (contains a package.json with a "workspaces" field), ask the user which package they wa…

No output schema declared.

No examples provided.

eyes_verify_api_key ~175

Validate your Applitools API key and optional server URL. Searches for API key in .env, applitools.config.js/ts/cjs/mjs, and playwright.config.js/ts/cjs/mjs files.

NameTypeReqDescription
apiKeystring–Optional API key to validate (will search config files if not provided)
serverUrlstring–Optional Applitools server URL (defaults to https://eyes.applitools.com)
setAsDefaultboolean–If true, save the validated API key and server URL as the default configuration in cache
workingDirectorystring–Working directory to search for .env and config files (optional, defaults to process.cwd())
workspaceRootstring–Workspace root to search for .env and config files (optional, defaults to current directory)

No output schema declared.

No examples provided.

Common questions

What is the Applitools MCP server?

Applitools is an MCP server listed in the public MCP registry as io.github.applitools/applitools. The Applitools MCP server helps you create, update, and analyze visual tests using Applitools Eyes. This page covers its npm package (@applitools/mcp).

Is the Applitools MCP server safe to use?

Applitools scores 77 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Applitools MCP server expose?

Applitools exposes 7 tools: eyes_verify_api_key, eyes_setup_project, eyes_setup_ufg, eyes_add_checkpoints_to_test, eyes_get_batch_url, and 2 more. Their descriptions and schemas cost roughly 2,120 tokens of context every time the server is loaded.

Is the Applitools MCP server still maintained?

Applitools is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.