webability MCP server
io.github.snayyar00/webabilitysnayyar00streamable-httpv1.11.1Scanned
Free WCAG 2.2/ADA/508 accessibility MCP: scan, AI fixes, verify, vision audit, localhost tunnel
17 tools: 11 change things and 6 only read.
- Reads private data · 1
- Reads text others write · 16
- Can send data out · 10
- 16 findings
Tools listed without sign-in. Remote posture
With Anlyon
11 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the webability MCP server can do
The webability MCP server is published by the GitHub account snayyar00. It has 17 tools. It can create or change data (11 tools: scan_page, verify_fix, start_audit, add_site and 7 more), but cannot delete data. 6 tools only read.
1 tool reads private data (diff_scan); 16 tools bring in text other people can write (scan_page, verify_fix, diff_scan and 13 more); 10 tools can send data out of your system (scan_page, verify_fix, diff_scan and 7 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 16 findings (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 1.11.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
17 tools
Changes things 11Claude Code: ask
add_siteAdd a website to the signed-in WebAbility account.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "add_site" says "add": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it Add a website to the signed-in WebAbility account. The site gets the full widget for its first 30 days and a first scan. Returns the site id and plan tier. Next: put the get_install_snippet tag on the site, and use create_upgrade_link to get a payment link for the WebAbility Pro plan. Needs a free WebAbility account (an AI agent can sign itself up with "Sign in with AgentID").
Annotations the server declares
- title: Add a site to the account
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
check_color_contrastCheck text contrast against the WCAG AA threshold (4.5:1, or 3:1 for large text); the AAA verdict is shown only when you pass level: "AAA".Reads text others writeCan send data out1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it Check text contrast against the WCAG AA threshold (4.5:1, or 3:1 for large text); the AAA verdict is shown only when you pass level: "AAA". Either pass a `foreground` / `background` color pair, or pass `url` + `selector` to read the element's own text color, background (composited from the nearest painted ancestors), font size and weight from the live page; explicit colors win over the page. A gradient or image background is reported as an error, never a guessed ratio. When it fails, suggests BRAND-aligned replacements — extracts the actual brand palette from the `url` page 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`.
Annotations the server declares
- title: Check color contrast
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
create_upgrade_linkGet a Stripe Checkout link that puts one site on the WebAbility Pro plan (the widget subscription).Reads text others write1 finding
Why it is in this group
- The name "create_upgrade_link" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it Get a Stripe Checkout link that puts one site on the WebAbility Pro plan (the widget subscription). Give the link to the human who pays (your owner). When they pay, the plan activates on that site automatically; check with list_sites. You never handle card details. The site must be on the account (add_site first). Needs a free WebAbility account.
Annotations the server declares
- title: Get a WebAbility Pro payment link
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
detect_frameworkDetect a page's stack as two separate fields: `framework` — the application framework, CMS or site builder (e.g.Reads text others writeCan send data out1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it Detect a page's stack as two separate fields: `framework` — the application framework, CMS or site builder (e.g. nextjs, nuxt, sveltekit, vitepress, astro, gatsby, wordpress, shopify, mediawiki, vue, react; "unknown" when no signal) — and `cssToolkit` (tailwind, bootstrap, mui, plain-css). Lists the evidence it used and the value to pass as generate_ai_fix `framework`. scan_page reports the same two fields from the same detection. 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`.
Annotations the server declares
- title: Detect the site framework
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
flow_scanScan a multi-page user journey.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it Scan a multi-page user journey. Walks startUrl plus the `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 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 / auth_redirect — storageState was given but the page is a sign-in page, session likely expired) — a page is never silently dropped. It only visits URLs: it does not click, type or log in. For pages behind a login, pass `storageState` (local MCP only), a session file saved after logging in once. Without `autoNavigate` it scans only startUrl, exactly like 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`.
Annotations the server declares
- title: Scan a multi-page user flow
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
generate_ai_fixGenerate framework-aware fix alternatives for a specific accessibility issue.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "generate_ai_fix" says "generate": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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`.
Annotations the server declares
- title: Suggest a framework-aware fix
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
scan_htmlScan 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 i…1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it 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. A snippet is capped at 256 KB, 300 elements and 100 nesting levels, and at 24s per call — past any of those the call is refused with the alternative to use; for a whole page use scan_page. Fragments are auto-wrapped into a document. Returns scan_page's shape (issues / 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`).
Annotations the server declares
- title: Scan an HTML snippet
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
scan_pageScan a web page for WCAG accessibility issues.Reads text others writeCan send data out1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it Scan a web page for WCAG accessibility issues. Works on any URL — deployed sites, localhost, staging. Returns `issues` (violations the scanner stands behind; findings the engines cannot decide are settled by the AI judge — a violation with a fix, or a pass recorded in `judged[]` with its reason — and anything unsettled is dropped, never listed for review) and a `summary`. 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`.
Annotations the server declares
- title: Scan a page for accessibility issues
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
start_auditKick off a FULL accessibility audit deliverable for a URL — a persistent, timestamped artifact, not an inline scan.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "start_audit" says "start": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it 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. structuredContent carries `{id, status, pollAfterSeconds, next, expiresAt}`; `expiresAt` is null until the API reports a retention time (download URLs last about 1 hour), and an unknown or expired id returns an `audit_not_found` error. 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. Needs a free WebAbility account (sign in by connecting https://mcp.webability.io/mcp/auth, 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.
Annotations the server declares
- title: Start a full accessibility audit
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
verify_fixRe-scan a specific element after applying an accessibility fix and confirm the violation is gone.Reads text others writeCan send data out1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it Re-scan a specific element after applying an accessibility fix and confirm the violation is gone. 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 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. verified: true is only returned when the selector matched at least one element AND the criterion is one the DOM engines check; if the selector matches no element the result is verified: false with reason "not-found" ("selector matched no elements"), a criterion outside the coverage set returns reason "not-verifiable" ("not checked by any WebAbility tool"); a finding in scope that only the AI judge can settle, when the judge did not run or gave no verdict, also returns "not-verifiable", and shadow-DOM (>>>) / iframe selectors return "unsupported-selector" — pass the element's current selector, or re-run scan_page if your fix removed the element. 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`.
Annotations the server declares
- title: Verify an accessibility fix
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
visual_auditPixel-level accessibility audit using Claude vision.Reads text others writeCan send data out1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it 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. Sign in with a free WebAbility account for vision and full audits (sign in by connecting https://mcp.webability.io/mcp/auth, 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`.
Annotations the server declares
- title: Visual accessibility audit
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 6Show 6 read-only tools
check_ariaValidate ARIA attribute + accessible name/role/value usage — in an HTML snippet (`html`) or on a live page (`url`), optionally limited to one element and its descendants (`selector…Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "validate": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it Validate ARIA attribute + accessible name/role/value usage — in an HTML snippet (`html`) or on a live page (`url`), optionally limited to one element and its descendants (`selector`). 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`. A selector that matches nothing, or a page that answers an HTTP error, is an error — never "no violations". Nodes cap at 5 per rule by default — every rule reports nodesTotal + truncated; raise nodeLimit (max 50). 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`.
Annotations the server declares
- title: Validate ARIA in HTML or on a page
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
diff_scanCompare 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 th…Reads private dataReads text others writeCan send data out1 finding
Why it is in this group
- The name "diff_scan" says "diff": a word for reading.
What it can reach
- private-dataThe input names a secret (input.tunnel_secret), and the tool reads: it reads secrets.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it 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`). Live scans run a second time when they differ, and a difference that does not hold goes to `unstable[]`, so a changed page can take twice as long. 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. 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`.
Annotations the server declares
- title: Compare two accessibility scans
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_auditCheck an audit started with start_audit: returns overall status, per-step progress (scan → viewports → screenshots → agent → excel → publish), and — once complete — a severity summ…Reads text others write1 finding
Why it is in this group
- The name "get_audit" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it 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.
Annotations the server declares
- title: Get audit status and report
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_install_snippetGet the one-line script tag that installs the WebAbility accessibility widget.Reads text others write1 finding
Why it is in this group
- The name "get_install_snippet" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "get" and "web": it reads web pages, which anyone can write.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it Get the one-line script tag that installs the WebAbility accessibility widget. Put it in the <head> or before </body> of every page of a site added with add_site. The widget finds the site by its domain, so the same tag works on every site. No account needed.
Annotations the server declares
- title: Get the widget install tag
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_rulesList accessibility rules from both engines — axe-core (104) and the WebAbility detectors (90+) — with optional filters.Reads text others write1 finding
Why it is in this group
- The name "get_rules" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "list" and "web": it reads web pages, which anyone can write.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it 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.
Annotations the server declares
- title: List accessibility rules
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_sitesList the sites on the signed-in WebAbility account with each site id, plan tier and the date the current plan ends.Reads text others write1 finding
Why it is in this group
- The name "list_sites" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "list" and "web": it reads web pages, which anyone can write.
Findings
- Info
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Description, as the server wrote it List the sites on the signed-in WebAbility account with each site id, plan tier and the date the current plan ends. Use it to check that a payment activated WebAbility Pro on a site. Needs a free WebAbility account.
Annotations the server declares
- title: List the account sites and plans
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
160 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write16
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out10
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__webability__diff_scan"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:11 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 11
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.webability.io/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://mcp.webability.io
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 11 tools that change things (11 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.webability.io/mcp: tools/list returned 17 tools to an anonymous client, including scan_page (write), verify_fix (write), start_audit (write), add_site (write), create_upgrade_link (write) and 6 more
Findings
Matches of fixed checks, with the text they matched.
- Infoscan_page
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
- Infoverify_fix
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
- Infodiff_scan
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
- Infostart_audit
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
- Infoadd_site
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
- Infolist_sites
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
Show 10 more findingsShow fewer
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
- Infoget_audit
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
- Infoflow_scan
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
- Infodetect_framework
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
- Infovisual_audit
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
- Infoscan_html
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
- Infoget_rules
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
- Infocheck_aria
The input schema at properties.context.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.context.description: "...es, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools5 changed.~5 changedView diff
- Changed:diff_scanOnly readsdescriptioninputSchema
- Changed:flow_scanChanges thingsinputSchema
- Changed:scan_htmlChanges thingsinputSchema
- Changed:scan_pageChanges thingsinputSchema
- Changed:start_auditChanges thingsdescription
Install
Pinned to version 1.11.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http webability https://mcp.webability.io/mcpclaude mcp add --transport http webability https://mcp.webability.io/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__webability__list_sites",
"mcp__webability__get_install_snippet",
"mcp__webability__get_audit",
"mcp__webability__get_rules"
],
"ask": [
"mcp__webability__scan_page",
"mcp__webability__verify_fix",
"mcp__webability__diff_scan",
"mcp__webability__start_audit",
"mcp__webability__add_site",
"mcp__webability__create_upgrade_link",
"mcp__webability__flow_scan",
"mcp__webability__detect_framework",
"mcp__webability__generate_ai_fix",
"mcp__webability__visual_audit",
"mcp__webability__scan_html",
"mcp__webability__check_color_contrast",
"mcp__webability__check_aria"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as webability. Review it before you use it.
Capability tags behind 16 rules
- mcp__webability__scan_page untrusted-input, outbound
- mcp__webability__verify_fix untrusted-input, outbound
- mcp__webability__diff_scan private-data, untrusted-input, outbound
- mcp__webability__start_audit untrusted-input, outbound
- mcp__webability__add_site untrusted-input, outbound
- mcp__webability__list_sites untrusted-input
- mcp__webability__get_install_snippet untrusted-input
- mcp__webability__create_upgrade_link untrusted-input
- mcp__webability__get_audit untrusted-input
- mcp__webability__flow_scan untrusted-input
- mcp__webability__detect_framework untrusted-input, outbound
- mcp__webability__generate_ai_fix untrusted-input, outbound
- mcp__webability__visual_audit untrusted-input, outbound
- mcp__webability__get_rules untrusted-input
- mcp__webability__check_color_contrast untrusted-input, outbound
- mcp__webability__check_aria untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.snayyar00/webability/verify?hash=5ac58c10770f622c2f3f672e08849091e697d261898f22715425d3f56f23e1ca" | jq -e '.changed == false'Pinned hash 5ac58c10770f, from Nov 20, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.snayyar00/webability/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.snayyar00/webability)Source: MCP Registry · repository. Synced Nov 20, 2026, 20:18 UTC.
webability MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the webability MCP server safe?
- No scan can promise that. What its definitions show: 17 tools, 11 of which can change, send or delete something, and 16 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the webability MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the webability MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the webability MCP server have?
- 17 tools: 11 write, 6 read. scan_page, verify_fix, start_audit, add_site, create_upgrade_link, flow_scan, detect_framework, generate_ai_fix and 9 more.
Does the webability MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the webability MCP server send data to outside services?
- 10 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): scan_page, verify_fix, diff_scan, start_audit, add_site, detect_framework and 4 more.
Has the webability MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.