Servidor MCP

webability

io.github.snayyar00/webability

Qué hace este MCP

Scans HTML and web pages for WCAG accessibility issues, performs visual audits and full reports, suggests and verifies fixes, and compares scan results.

check_aria
Validate ARIA in HTML
Validate ARIA attribute + accessible name/role/value usage in an HTML snippet. Runs axe-core `cat.aria` and `cat.name-role-value` rules (aria-* attribute correctness, role validity, required parents/children, aria-hidden-focus, accessible names). Returns `violations` (high-confidence) and `incomplete` (needs human review, e.g. dangling ARIA references — do NOT auto-fix). Nodes cap at 5 per rule by default — every rule reports nodesTotal + truncated; raise nodeLimit (max 50).
Solo lectura Idempotente
Esquema de entrada
{'type': 'object', 'required': ['html'], 'properties': {'html': {'type': 'string', 'description': 'HTML to test for ARIA correctness'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'nodeLimit': {'type': 'number', 'description': 'Max nodes returned per rule (default 5, max 50)'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
check_color_contrast
Check color contrast
Check a foreground/background color pair against WCAG contrast thresholds. When it fails, suggests BRAND-aligned replacements — extracts the actual brand palette from a live URL using our scanner (CSS vars + most-used colors), or use a provided `brandColors` array. No `url` and no `brandColors` = ratio + pass/fail only. NOTE: on this HOSTED server, localhost and private addresses are refused — it runs in our cloud and cannot reach your machine. Two ways to scan a local dev server: run the MCP locally (`npx -y @webability/mcp`, simplest — nothing leaves the machine), or open a tunnel (`webability-tunnel --port 3000`) and pass its URL as `url` together with the printed secret as `tunnel_secret`.
Solo lectura Acceso externo Idempotente
Esquema de entrada
{'type': 'object', 'required': ['foreground', 'background'], 'properties': {'url': {'type': 'string', 'description': 'Live URL to extract brand palette from (uses our scanner — CSS vars + dominant colors).'}, 'isBold': {'type': 'boolean', 'description': 'Whether text is bold (default false)'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'fontSize': {'type': 'number', 'description': 'Font size in px (default 16)'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'background': {'type': 'string', 'description': 'Background color (hex or rgb)'}, 'foreground': {'type': 'string', 'description': 'Foreground color (hex or rgb)'}, 'brandColors': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Pre-supplied brand palette. Skips URL extraction if provided.'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
detect_framework
Detect the site framework
Detect which framework/stack a page uses (Tailwind, MUI, Bootstrap, WordPress, Next.js, plain CSS). Use before generate_ai_fix to get framework-appropriate code. NOTE: on this HOSTED server, localhost and private addresses are refused — it runs in our cloud and cannot reach your machine. Two ways to scan a local dev server: run the MCP locally (`npx -y @webability/mcp`, simplest — nothing leaves the machine), or open a tunnel (`webability-tunnel --port 3000`) and pass its URL as `url` together with the printed secret as `tunnel_secret`.
Solo lectura Acceso externo Idempotente
Esquema de entrada
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'URL to inspect'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
diff_scan
Compare two accessibility scans
Compare two scans of the same page and report what changed: `fixed[]` (in the baseline, gone now), `new[]` (regressions — not in the baseline, present now), `remaining[]` (still there). Page-level complement to verify_fix (one element). Baseline is a scan_history id (`baselineId`, local installs) or a live scan of `baselineUrl`; current is `url` (scanned live now) or another history id (`currentId`). Findings are matched by issue id (rule + element), so a changed class/id on a fixed element reads as fixed AND new — check `new[]` before calling it a regression. Needs-review findings are diffed separately (`incompleteResolved` / `incompleteNew`) and never counted as fixed. Typical loop: scan_page → edit → diff_scan(baselineId=<that scan id>, url=<same url>) → confirm new[] is empty. NOTE: on this HOSTED server, localhost and private addresses are refused — it runs in our cloud and cannot reach your machine. Two ways to scan a local dev server: run the MCP locally (`npx -y @webability/mcp`, simplest — nothing leaves the machine), or open a tunnel (`webability-tunnel --port 3000`) and pass its URL as `url` together with the printed secret as `tunnel_secret`.
Solo lectura Acceso externo Idempotente
Esquema de entrada
{'type': 'object', 'required': [], 'properties': {'url': {'type': 'string', 'description': 'URL to scan now as the CURRENT side (deployed, staging, or http://localhost:3000). Omit when passing currentId.'}, 'wcag': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these WCAG criteria. A prefix selects the whole guideline ("1.4") or principle ("2").'}, 'rules': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these rule ids (WebAbility type such as "missing_alt" or axe rule id such as "image-alt"). See get_rules.'}, 'format': {'enum': ['json', 'compact'], 'type': 'string', 'description': '"compact" prints one line per element with rule metadata once. "json" returns every field (html, fix values, source). Default: JSON when it fits inline (under ~24k chars), otherwise compact plus a JSON summary of every count.'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'viewport': {'enum': ['desktop', 'tablet', 'mobile'], 'type': 'string', 'description': 'Viewport for live scans (default: desktop). Use the same viewport the baseline used.'}, 'currentId': {'type': 'string', 'description': 'scan_history id to use as the CURRENT side instead of scanning `url`'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'minImpact': {'enum': ['critical', 'serious', 'moderate', 'minor'], 'type': 'string', 'description': 'Only findings at this severity or above (critical > serious > moderate > minor)'}, 'baselineId': {'type': 'string', 'description': 'scan_history id of the BASELINE scan (local installs only)'}, 'baselineUrl': {'type': 'string', 'description': 'Scan this URL live as the baseline (e.g. production) — use when there is no stored baseline'}, 'rootSelector': {'type': 'string', 'description': 'CSS selector to limit live scans to (optional)'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
flow_scan
Scan a multi-page user flow
Scan a multi-page user journey. Walks startUrl plus the required `autoNavigate` URLs sequentially (deterministic — one page fully rendered and scanned before the next), then returns ONE consolidated report with issues deduplicated across pages, each carrying the same fix payload / confidence / review flags as scan_page. Every requested URL gets an explicit outcome in `pages[]` (scanned / nav_failed / scan_failed / redirected_duplicate / duplicate_request / skipped_cap / blocked — bot-challenge, not a clean page) — a page is never silently dropped. Better than per-page scans for journeys (login → checkout etc). For a single page, use scan_page. NOTE: on this HOSTED server, localhost and private addresses are refused — it runs in our cloud and cannot reach your machine. Two ways to scan a local dev server: run the MCP locally (`npx -y @webability/mcp`, simplest — nothing leaves the machine), or open a tunnel (`webability-tunnel --port 3000`) and pass its URL as `url` together with the printed secret as `tunnel_secret`.
Solo lectura Acceso externo Idempotente
Esquema de entrada
{'type': 'object', 'required': ['startUrl', 'autoNavigate'], 'properties': {'wcag': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these WCAG criteria. A prefix selects the whole guideline ("1.4") or principle ("2").'}, 'rules': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these rule ids (WebAbility type such as "missing_alt" or axe rule id such as "image-alt"). See get_rules.'}, 'format': {'enum': ['json', 'compact'], 'type': 'string', 'description': '"compact" prints one line per element with rule metadata once. "json" returns every field (html, fix values, source). Default: JSON when it fits inline (under ~24k chars), otherwise compact plus a JSON summary of every count.'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'maxPages': {'type': 'number', 'description': 'Max pages to scan (default 10)'}, 'startUrl': {'type': 'string', 'description': 'Starting URL of the journey'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'minImpact': {'enum': ['critical', 'serious', 'moderate', 'minor'], 'type': 'string', 'description': 'Only findings at this severity or above (critical > serious > moderate > minor)'}, 'sourceRoot': {'type': 'string', 'description': 'Local project root (local installs only) for `sourceCandidates[]` on issues without a framework `source` pointer.'}, 'autoNavigate': {'type': 'array', 'items': {'type': 'string'}, 'description': 'REQUIRED — the URLs to walk after startUrl (the MCP server is headless and cannot discover a journey interactively). For a single page, use scan_page instead.'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
generate_ai_fix
Suggest a framework-aware fix
Generate framework-aware fix alternatives for a specific accessibility issue. For color contrast issues, returns 3 alternatives (minimal, brand-aligned, high contrast); brand palette is auto-extracted from the live URL using our scanner if `brandColors` is omitted. For label/ARIA issues, returns 1-2 alternatives. Each alternative includes ready-to-paste code for the detected framework. NOTE: on this HOSTED server, localhost and private addresses are refused — it runs in our cloud and cannot reach your machine. Two ways to scan a local dev server: run the MCP locally (`npx -y @webability/mcp`, simplest — nothing leaves the machine), or open a tunnel (`webability-tunnel --port 3000`) and pass its URL as `url` together with the printed secret as `tunnel_secret`.
Acceso externo
Esquema de entrada
{'type': 'object', 'required': ['issue', 'html', 'framework'], 'properties': {'url': {'type': 'string', 'description': 'Page URL — also used to auto-extract brand palette for contrast issues if `brandColors` is not provided.'}, 'html': {'type': 'string', 'description': "The element's outerHTML — send at most ~600 chars"}, 'issue': {'type': ['object', 'string'], 'description': 'Issue object from scan_page (with selector, wcag, impact, message, fix.currentValue), or a plain-text issue description'}, 'context': {'type': 'string', 'description': 'Parent element outerHTML for context (~400 chars)'}, 'framework': {'enum': ['tailwind', 'bootstrap', 'mui', 'wordpress', 'nextjs', 'plain-css'], 'type': 'string', 'description': 'CSS framework — use detect_framework first'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'brandColors': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Brand palette for brand-aligned suggestions. If omitted on a contrast issue with a `url`, auto-extracted via the scanner.'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
get_audit
Get audit status and report
Check an audit started with start_audit: returns overall status, per-step progress (scan → viewports → screenshots → agent → excel → publish), and — once complete — a severity summary plus short-lived download URLs for the report (JSON) and the Excel workbook. Poll every ~15s while status is pending/running. Only the account that started an audit can read it. Free with a WebAbility account.
Solo lectura Acceso externo Idempotente
Esquema de entrada
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'number', 'description': 'The audit id returned by start_audit'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
get_rules
List accessibility rules
List accessibility rules from both engines — axe-core (104) and the WebAbility detectors (90+) — with optional filters. Every rule carries `fixability` (mechanical | contextual | visual) and a `fix` op template, so you can pick the rules worth auto-fixing before scanning. Returns ruleId, engine, description, help, helpUrl, tags/wcag, fixability, fix.
Solo lectura Idempotente
Esquema de entrada
{'type': 'object', 'required': [], 'properties': {'rule': {'type': 'string', 'description': 'Only rules whose id contains this text (e.g. "color-contrast", "label"; case and -/_ insensitive). Also accepted: ruleId, id, query.'}, 'tags': {'type': 'array', 'items': {'type': 'string'}, 'description': 'axe tag filter (e.g. ["wcag21aa"], ["best-practice"], ["cat.aria"]). WebAbility rules match on their WCAG criterion tag (e.g. "wcag143").'}, 'engine': {'enum': ['all', 'axe', 'webability'], 'type': 'string', 'description': "Which engine's rules to list (default all)"}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'fixability': {'enum': ['mechanical', 'contextual', 'visual'], 'type': 'string', 'description': 'Only rules of this fixability tier'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
scan_html
Scan an HTML snippet
Scan a raw HTML snippet or component markup without serving it — IN-PROCESS by default (jsdom + WebAbility detectors + axe-core): milliseconds, no browser, no network, so it fits inside a tight edit loop. Fragments are auto-wrapped into a document. Returns scan_page's three-tier shape (issues / incomplete / summary) with `fix.op` + `fixability` on every finding. jsdom has no layout, so visual-tier rules (contrast, target size, focus ring) are NOT evaluated — the dropped count is reported as `skippedVisual`; pass `engine: "browser"` to run the axe-core headless-browser path for those (slower, axe rules only, returns axe `violations`).
Solo lectura Idempotente
Esquema de entrada
{'type': 'object', 'required': ['html'], 'properties': {'html': {'type': 'string', 'description': 'HTML content to test — a full document or a fragment'}, 'tags': {'type': 'array', 'items': {'type': 'string'}, 'description': 'WCAG tags to check (default ["wcag2a","wcag2aa","wcag21aa","wcag22aa"])'}, 'wcag': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these WCAG criteria. A prefix selects the whole guideline ("1.4") or principle ("2").'}, 'rules': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these rule ids (WebAbility type such as "missing_alt" or axe rule id such as "image-alt"). See get_rules.'}, 'width': {'type': 'number', 'description': 'Viewport width (browser engine only, default 1280)'}, 'engine': {'enum': ['in-process', 'browser'], 'type': 'string', 'description': '"in-process" (default): jsdom, ms, structural rules. "browser": headless Chromium + axe-core, includes contrast.'}, 'format': {'enum': ['json', 'compact'], 'type': 'string', 'description': '"compact" prints one line per element with rule metadata once. "json" returns every field (html, fix values, source). Default: JSON when it fits inline (under ~24k chars), otherwise compact plus a JSON summary of every count.'}, 'height': {'type': 'number', 'description': 'Viewport height (browser engine only, default 800)'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'minImpact': {'enum': ['critical', 'serious', 'moderate', 'minor'], 'type': 'string', 'description': 'Only findings at this severity or above (critical > serious > moderate > minor)'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
scan_page
Scan a page for accessibility issues
Scan a web page for WCAG accessibility issues. Works on any URL — deployed sites, localhost, staging. Returns the three-tier shape: `issues` (high-confidence violations safe to fix), `incomplete` (needs human review — gradient backgrounds, marketing imagery, axe-incomplete results, framer-motion pre-animation states), and a `summary`. Treat `incomplete` as questions, never auto-fix them. On React ≤18 / Vue dev builds each issue carries `source` ({file, line, column, component}) read from the live component tree. Every issue carries a structured `fix.op` (add-attribute | set-attribute | remove-attribute | add-element | remove-element | add-text-content | suggest) with `fix.attribute` / `fix.value` when known, and a `fixability` tier (mechanical = apply as given; contextual = op known, value needs judgment; visual = needs rendered output, propose only). NOTE: on this HOSTED server, localhost and private addresses are refused — it runs in our cloud and cannot reach your machine. Two ways to scan a local dev server: run the MCP locally (`npx -y @webability/mcp`, simplest — nothing leaves the machine), or open a tunnel (`webability-tunnel --port 3000`) and pass its URL as `url` together with the printed secret as `tunnel_secret`.
Solo lectura Acceso externo Idempotente
Esquema de entrada
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'URL to scan (e.g. https://example.com or http://localhost:3000)'}, 'wcag': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these WCAG criteria. A prefix selects the whole guideline ("1.4") or principle ("2").'}, 'rules': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these rule ids (WebAbility type such as "missing_alt" or axe rule id such as "image-alt"). See get_rules.'}, 'format': {'enum': ['json', 'compact'], 'type': 'string', 'description': '"compact" prints one line per element with rule metadata once. "json" returns every field (html, fix values, source). Default: JSON when it fits inline (under ~24k chars), otherwise compact plus a JSON summary of every count.'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'viewport': {'enum': ['desktop', 'tablet', 'mobile'], 'type': 'string', 'description': 'Viewport size (default: desktop)'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'minImpact': {'enum': ['critical', 'serious', 'moderate', 'minor'], 'type': 'string', 'description': 'Only findings at this severity or above (critical > serious > moderate > minor)'}, 'sourceRoot': {'type': 'string', 'description': "Local project root (local installs only). Issues without a framework `source` pointer get `sourceCandidates[]` — files whose contents match the selector's id/class/attribute tokens."}, 'rootSelector': {'type': 'string', 'description': 'CSS selector to limit scan scope (optional)'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
start_audit
Start a full accessibility audit
Kick off a FULL accessibility audit deliverable for a URL — a persistent, timestamped artifact, not an inline scan. Runs the server-side pipeline (axe + advanced checks + mobile viewports + annotated screenshots + optional agent spot-check) and produces a downloadable report and a formatted Excel workbook (Cover / Status / Barriers / ADA context sheets) stored durably. Returns immediately with an audit `id`; poll `get_audit` for progress and, when complete, download URLs. Use this when someone needs a durable artifact to attach as evidence of testing effort for a compliance officer or legal response — for iterating on code, use scan_page + verify_fix instead. Free for everyone; needs a free WebAbility account (sign in when your client prompts you, or run `webability login`). Set includeAgent:true to add the slower agentic manual-audit pass. To audit a local dev server, open a tunnel (`webability-tunnel --port 3000`) and pass its URL as `url` with the printed secret as `tunnel_secret`; keep the tunnel open until get_audit reports complete (about 5 minutes) — the pipeline loads the page several times.
Acceso externo
Esquema de entrada
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'URL to audit (a public/staging URL the server can reach, or a webability-tunnel URL — not localhost)'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'includeAgent': {'type': 'boolean', 'description': 'Also run the agentic manual-audit pass (keyboard/focus/modal exploration). Slower. Default false.'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
verify_fix
Verify an accessibility fix
Re-scan a specific element after applying an accessibility fix and confirm the violation is gone — closes the loop that find-only tools leave open. After you edit the code and serve it (deployed, staging, or http://localhost:3000), call this with the URL and the selector you fixed to get a machine-checked verified: true|false (DOM engines only — visual_audit findings and needs-review items are out of scope). Pass the WCAG criterion (e.g. "1.1.1") or axe rule id (e.g. "color-contrast") to check just that criterion; omit it to require the element be clean of ALL violations. A blocked page (bot-challenge / HTTP error) is reported as unverified, never a pass — verification fails closed. IMPORTANT: if your fix changed the element's class or id, the original selector may no longer match anything, which reads as verified — re-run scan_page or pass the updated selector to be sure. Pair with scan_page → generate_ai_fix → verify_fix for a full find-fix-verify cycle. NOTE: on this HOSTED server, localhost and private addresses are refused — it runs in our cloud and cannot reach your machine. Two ways to scan a local dev server: run the MCP locally (`npx -y @webability/mcp`, simplest — nothing leaves the machine), or open a tunnel (`webability-tunnel --port 3000`) and pass its URL as `url` together with the printed secret as `tunnel_secret`.
Solo lectura Acceso externo Idempotente
Esquema de entrada
{'type': 'object', 'required': ['url', 'selector'], 'properties': {'url': {'type': 'string', 'description': 'URL now serving the fix (deployed, staging, or http://localhost:3000). Also accepted as `page` or `pageUrl`.'}, 'wcag': {'type': 'string', 'description': 'Optional: WCAG criterion (e.g. "1.1.1", "1.4.3") or axe rule id (e.g. "color-contrast") to verify specifically. Omit to require the element be free of ALL violations.'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'selector': {'type': 'string', 'description': 'CSS selector of the element you fixed — use the `selector` from the original scan_page issue'}, 'viewport': {'enum': ['desktop', 'tablet', 'mobile'], 'type': 'string', 'description': 'Viewport size (default: desktop). Use the same viewport the issue was found at.'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
visual_audit
Visual accessibility audit
Pixel-level accessibility audit using Claude vision. Catches issues that DOM scanners miss: icon contrast (1.4.11), focus visibility (2.4.7), "looks like a button but isn't" (4.1.2), text rendered as images (1.4.5), visual hierarchy mismatches. Takes a URL, opens it in a headless browser, screenshots, and runs vision-based detection. Complements scan_page — run both for full coverage. Free for everyone; sign in with a free WebAbility account for vision and full audits (sign in when your client prompts you, or run `webability login`). Fair-use rate limits apply. NOTE: on this HOSTED server, localhost and private addresses are refused — it runs in our cloud and cannot reach your machine. Two ways to scan a local dev server: run the MCP locally (`npx -y @webability/mcp`, simplest — nothing leaves the machine), or open a tunnel (`webability-tunnel --port 3000`) and pass its URL as `url` together with the printed secret as `tunnel_secret`.
Acceso externo
Esquema de entrada
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'URL to audit visually'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'fullPage': {'type': 'boolean', 'description': 'Capture full scrolled page instead of just viewport (default: false)'}, 'viewport': {'enum': ['desktop', 'tablet', 'mobile'], 'type': 'string', 'description': 'Viewport size (default: desktop)'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'brandColors': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Brand hex colors for context-aware filtering'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Añadido
check_aria
5 de October de 2026 a las 02:40
Añadido
check_color_contrast
5 de October de 2026 a las 02:40
Añadido
get_rules
5 de October de 2026 a las 02:40
Añadido
scan_html
5 de October de 2026 a las 02:40
Añadido
visual_audit
5 de October de 2026 a las 02:40
Añadido
generate_ai_fix
5 de October de 2026 a las 02:40
Añadido
detect_framework
5 de October de 2026 a las 02:40
Añadido
flow_scan
5 de October de 2026 a las 02:40
Añadido
get_audit
5 de October de 2026 a las 02:40
Añadido
start_audit
5 de October de 2026 a las 02:40
Añadido
diff_scan
5 de October de 2026 a las 02:40
Añadido
verify_fix
5 de October de 2026 a las 02:40
Añadido
scan_page
5 de October de 2026 a las 02:40