Atlas / MCP servers / justasmonkev / Accessibility Scanner

Accessibility ScannerBLOCK

mcp/justasmonkev/accessibility-scanner

An MCP (Model Context Protocol) server for performing accessibility audits on webpages using axe-core.

Verdict
BLOCK
Grade
D
Trust score
61 /100
Exposed tools
72 58r · 12w · 2d
Transport
stdio · streamable-http
License
MIT
Stars
57
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://mcptoplist.com/server/io.github.JustasMonkev%2Fmcp-accessibility-scanner)

Star History

[](https://api.star-history.com/svg?repos=justasmonkev%2Fmcp-accessibility-scanner&type=Date)

[](https://mseep.ai/app/justasmonkev-mcp-accessibility-scanner)

A Model Context Protocol (MCP) server for accessibility scanning and browser automation with Playwright and Axe-core. It supports page interaction, persistent browser sessions, and accessibility reports with visual annotations.

Features

Accessibility Scanning

✅ Automated checks for WCAG 2.0/2.1/2.2 criteria (A, AA, AAA levels)\ 📄 Detailed JSON reports with remediation guidance 🎯 Support for specific violation categories (color contrast, ARIA, forms, keyboard navigation, etc.)

Browser Automation

🖱️ Click, hover, and drag elements using accessibility snapshots ⌨️ Type text and handle keyboard inputs 🔍 Capture page snapshots to discover all interactive elements 📸 Take screenshots and save PDFs 🎯 Support for both element-based and coordinate-based interactions

Advanced Features

📑 Tab management for multi-page workflows 🌐 Monitor console messages and network requests ⏱️ Wait for dynamic content to load 📁 Handle file uploads and browser dialogs 🔄 Navigate through browser history

Installation

You can install the package using any of these methods:

Using npm:

npm install -g mcp-accessibility-scanner --allow-scripts=re2

npm 12 does not run dependency install scripts unless you allow them. The scanner depends on `re2`, a native module whose install script downloads or builds `re2.

Read from source at commit 6d75b67cce8cOBSERVED · 2026-10-08
Advertisement
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add mcp-accessibility-scanner --env PLAYWRIGHT_MCP_AUTH_TOKEN=${PLAYWRIGHT_MCP_AUTH_TOKEN} --env PLAYWRIGHT_MCP_EXTENSION_TOKEN=${PLAYWRIGHT_MCP_EXTENSION_TOKEN} --env PLAYWRIGHT_MCP_PROXY_BYPASS=${PLAYWRIGHT_MCP_PROXY_BYPASS} -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "mcp-accessibility-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "PLAYWRIGHT_MCP_AUTH_TOKEN": "${PLAYWRIGHT_MCP_AUTH_TOKEN}",
        "PLAYWRIGHT_MCP_EXTENSION_TOKEN": "${PLAYWRIGHT_MCP_EXTENSION_TOKEN}",
        "PLAYWRIGHT_MCP_PROXY_BYPASS": "${PLAYWRIGHT_MCP_PROXY_BYPASS}"
      }
    }
  }
}
03

Exposed tools (72)

58 read · 12 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
absentreadabsent
alternatereadAlternate provider
audit-keyboard-reportreadJSON report for keyboard navigation, focus, and skip-link findings.
audit-screen-reader-reportwriteJSON report for accessible name quality and reading order findings.
audit-site-reportreadAggregated JSON report for the site accessibility crawl.
audit_keyboardwriteAudit keyboard tab order, focus visibility, jumps, skip links, and focus traps.
audit_screen_readerwriteAudit accessible name quality and reading order using the browser accessibility tree and element geometry.
audit_sitereadCrawl internal pages and aggregate accessibility violations across the site.
browser_clickreadPerform click on a web page
browser_closereadClose the page
browser_connectreadDo not call, this tool is used in the integration with the Playwright VS Code Extension and meant for programmatic usage only.
browser_console_messagesreadReturns all console messages
browser_default_timeoutreadSets the default timeout for all Playwright operations (clicks, fills, etc). Only affects existing tabs and does not persist across browser context recreation.
browser_dragdestructivePerform drag and drop between two elements
browser_dropdestructiveSimulate an external drag and drop of files or clipboard-like data onto an element
browser_emulate_mediareadEmulate CSS media features for the page. Omitted parameters keep their current state.
browser_evaluatereadEvaluate JavaScript expression on page or element
browser_file_uploadwriteUpload one or multiple files
browser_fill_formreadFill multiple form fields
browser_findreadSearch the accessibility snapshot of the current page for text or a regular expression. Returns matching snapshot nodes with a few lines of surrounding context, each shown under its path from the root of the tree.
browser_handle_dialogreadHandle a dialog
browser_hoverreadHover over element on page
browser_installwriteInstall the browser specified in the config. Call this if you get an error about the browser not being installed.
browser_mouse_click_xyreadClick mouse button at a given position
browser_mouse_drag_xyreadDrag left mouse button to a given position
browser_mouse_move_xywriteMove mouse to a given position
browser_navigatereadNavigate to a URL
browser_navigate_backreadGo back to the previous page
browser_navigation_timeoutreadSets the timeout for navigation and page load actions. Only affects the current tab and does not persist across browser context recreation.
browser_network_requestreadReturns credential-redacted headers and body metadata for a single network request listed by browser_network_requests
browser_network_requestsreadReturns all network requests since loading the page
browser_pdf_savewriteSave page as PDF
browser_press_keyreadPress a key on the keyboard
browser_resizereadResize the browser window
browser_select_optionreadSelect an option in a dropdown
browser_session_closereadClose a browser session previously opened with browser_session_open and release its browser resources. The default session cannot be closed this way.
browser_snapshotreadCapture accessibility snapshot of the current page, this is better than screenshot
browser_start_recordingwriteStart recording actions that the user performs in the browser as Playwright code. Call browser_stop_recording when the user is done.
browser_stop_recordingwriteStop the recording started with browser_start_recording and return the recorded actions as Playwright code.
browser_tabswriteList, create, close, or select a browser tab.
browser_take_screenshotreadTake a screenshot of the current page. You can
browser_typereadType text into editable element
browser_verify_element_visiblereadVerify element is visible on the page
browser_verify_list_visiblereadVerify list is visible on the page
browser_verify_text_visiblereadVerify text is visible on the page. Prefer ${verifyElement.schema.name} if possible.
browser_verify_valuereadVerify element value
browser_wait_forreadWait for text to appear or disappear or a specified time to pass. When both text and textGone are provided, waits for the first one to happen
defaultreadStarts standalone browser
duplicatereadfirst
echoreadchanged
extensionreadConnect to a browser using the Playwright MCP extension
forgedread
hangreadhang-${index}
idempotent_state_changereadConverges to the requested state
identityreadIdentity tool
my_toolreadDescription
native_echoreadnative-frame-${index}
prepareread
probereadProbe tool
replacementreadReplacement
reportreadTest report
scan-page-annotated-screenshotreadFull-page screenshot with violating elements outlined and labelled with their rule id.
scan-page-matrix-reportreadJSON report containing per-variant Axe results and baseline deltas.
scan_pagereadScan the current page for accessibility violations using Axe
scan_page_matrixwriteRun accessibility scans across viewport/media/zoom variants and compare with baseline.
shared_echoreadshared document
state_changingreadState-changing tool
tab_toolreadA tab tool
test_readreadRead-only tool
test_toolreadA test tool
test_writewriteDestructive tool
tool_alternatereada
04

Trust audit

BLOCKgrade D · trust 61/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)FAIL
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (5 observation(s))
Network
declared (8 observation(s))
Shell
declared (3 observation(s))
Dependencies
not all pinned
Secrets in source
found

Findings (25)

CRITICALPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
SKILL.md:129
**Behind a login:** the crawl shares the browser context, so signing in with `browser_navigate` / `browser_fill_form` first is enough. Alternatively record a session with `npx [email protected] codege
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
.codex/run-mcp-direct-harness.mjs:1078
'location': `http://127.0.0.1:${state.deadPort}/gone`,
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
.codex/run-mcp-direct-harness.mjs:1120
state.fixtureOrigin = `http://127.0.0.1:${address.port}`;
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
.codex/run-mcp-tool-loop.mjs:275
resolve({ url: `http://127.0.0.1:${address.port}/audit-site`, close: () => closeFixtureServer(server) });
MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321
tests/program.test.ts:173
const secret = 'startup-secret-do-not-print';
MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
browser_drag, browser_drop
Why it matters. 2 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
LOWInventory / provenance · inv.hidden_file · CWE-1104
.oxlintrc.json
.oxlintrc.json
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
graphify-out/.graphify_labels.json
.graphify_labels.json
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
graphify-out/.graphify_python
.graphify_python
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
graphify-out/.graphify_root
.graphify_root
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/tools-codegen.test.ts:44
expect(() => new Function('page', `return async () => {\n${response.code()}\n};`)).not.toThrow();
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/tools-evaluate.test.ts:217
expect(() => new Function(`return ${wrapped}`)).not.toThrow();
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/tools-evaluate.test.ts:228
expect(() => new Function(`return ${toFunctionSource(source, onElement)}`)).not.toThrow();
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/tools-form.test.ts:38
await new Function('page', `return (async () => { ${response.code()} })();`)(page);
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/tools-wait.test.ts:95
await new Function('page', `return (async () => { ${response.code()} })();`)(page);
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/mcp/toolPolicy.ts:18
import type { Config } from '../../config.js';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/tools/tool.ts:20
import type { ToolCapability } from '../../config.js';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
tests/config.test.ts:491
it.each(['my-profile', 'Default/../../etc', 'Profile 1 ', ''])('rejects an invalid profile directory name from the CLI: %s', async profileDirName => {
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
tests/config.test.ts:739
const result = await outputFile(config, 'test/../../../etc/passwd');
LOWNetwork egress · net.metadata_ip · CWE-200, CWE-319
tests/tools-auditSite.test.ts:1360
'https://169.254.169.254/latest/sitemap.xml': '<urlset><url><loc>https://example.com/one</loc></url></urlset>',
Why it matters. cloud metadata endpoint: the classic SSRF credential grab
LOWNetwork egress · net.metadata_ip · CWE-200, CWE-319
tests/tools-auditSite.test.ts:1366
sitemapUrl: 'https://169.254.169.254/latest/sitemap.xml',
Why it matters. cloud metadata endpoint: the classic SSRF credential grab
LOWNetwork egress · net.metadata_ip · CWE-200, CWE-319
tests/tools-auditSite.test.ts:1456
const redirectTarget = 'https://169.254.169.254/latest/sitemap.xml';
Why it matters. cloud metadata endpoint: the classic SSRF credential grab
LOWNetwork egress · net.metadata_ip · CWE-200, CWE-319
tests/tools-auditSite.test.ts:1459
network: { blockedOrigins: ['169.254.169.254'] },
Why it matters. cloud metadata endpoint: the classic SSRF credential grab
LOWNetwork egress · net.metadata_ip · CWE-200, CWE-319
tests/vscode-validation.test.ts:78
'ws://169.254.169.254/',
Why it matters. cloud metadata endpoint: the classic SSRF credential grab
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
.codex/skills/pre-push-review/references/codex-findings-catalog.md:32
- Advertised vs enforced: with `--host 0.0.0.0` the server printed `http://0.0.0.0:<port>/mcp`, but its own Host-header allowlist rejected that Host with 403; earlier, wildcard binds never added inter

Gates applied: critical_finding, no_behavioural_pass, undeclared_transfer.

Audited 2026-10-08 · audit v0.4.1 · source sha 6d75b67cce8cfull audit observations/trust-audit/mcp-server/justasmonkev__accessibility-scanner.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-086d75b67cce8cBLOCKD61first audit
06

Questions

What is the Accessibility Scanner MCP server?

An MCP (Model Context Protocol) server for performing accessibility audits on webpages using axe-core.

What tools does Accessibility Scanner expose?

72 in total: 58 read-only, 12 that write, and 2 that can delete or overwrite (browser_drag, browser_drop). Every one is listed on this page with its risk.

Is Accessibility Scanner safe to connect to an agent?

No — not without reading the findings first. The audit graded it D (61/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Accessibility Scanner need?

It reads PLAYWRIGHT_MCP_AUTH_TOKEN, PLAYWRIGHT_MCP_EXTENSION_TOKEN and PLAYWRIGHT_MCP_PROXY_BYPASS from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Accessibility Scanner run?

It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as mcp-accessibility-scanner at 4.0.0.

How current is this page?

The grade is for one exact copy of the source (6d75b67cce8c), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement