mcpField
W
wcagc — accessibility scanning

wcagc — accessibility scanning

Remote
wcagc.comDeveloper Tools0Updated 2d ago

About wcagc — accessibility scanning

wcagc-mcp is a stateless adapter for running deterministic accessibility scans through wcagc. It serves teams that need scan results and findings, while clearly noting that automated checks do not establish conformance.

Key features

  1. 01Scan public URLs with axe-core
  2. 02Check public PDFs for PDF/UA-1 structure
  3. 03Read scan status, severity counts and findings
  4. 04Crawl registered sites and review run results
  5. 05Group repeated DOM patterns and inspect impact
  6. 06Replay saved journeys and view violation trends

Use cases

  1. 01Check a public page for accessibility issues
  2. 02Inspect PDF structure against PDF/UA-1
  3. 03Review findings across a registered site's crawl
  4. 04Track recurring patterns or site violation history

MCP support

Exposes wcagc scan and result-management tools to MCP clients. It supports local stdio and hosted Streamable HTTP with managed OAuth.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.wcagc.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
npm@wcagc/mcp0.8.0

Tools

Details

From the project README

wcagc-mcp

WCAG-Compliance/wcagc-mcp MCP server smithery badge

An MCP server that lets an AI assistant (Claude, ChatGPT, or any MCP-compatible client) run real, deterministic accessibility scans through wcagc — axe-core under the hood, not an LLM guess. Every scan result carries an explicit coverage disclaimer and never claims "compliant": automated testing finds only a portion of accessibility barriers, and this tool says so in every response.

This package is a thin, stateless adapter. It holds no database, no scan logic, and no secrets beyond the wcagc API base URL — it translates MCP tool calls into HTTP calls against the wcagc API and forwards the caller's own bearer. All authentication, entitlements, quotas, and scan orchestration live in the API; this code is safe to read end to end.

Two ways to run it

Local (stdio) — for Claude Desktop, Cursor, or any MCP client that spawns a local process:

npx @wcagc/mcp

Configure your MCP client with:

{
  "mcpServers": {
    "wcagc": {
      "command": "npx",
      "args": ["-y", "@wcagc/mcp"],
      "env": {
        "WCAGC_MCP_KEY": "<your mcp:scan API key>"
      }
    }
  }
}

Mint an mcp:scan key from your wcagc account under Settings → API keys — available on every plan, with a daily quota on Free/Starter and unlimited on Pro/Agency.

Hosted (Streamable HTTP + managed OAuth) — what Claude web/desktop/mobile connectors and ChatGPT use, since neither runs a local process for you. Add this remote MCP connector:

https://mcp.wcagc.com/mcp

The client discovers /.well-known/oauth-protected-resource/mcp, opens the wcagc login/consent flow, and binds the connection to one Organization. No key copy/paste is required. API-key bearer authentication remains supported for local stdio and CI.

ChatGPT availability depends on the ChatGPT plan and on whether the client permits action tools; scan_url creates a scan and is not a read-only operation. See wcagc.com/integrations/mcp.

Tools

ToolPlanWhat it does
scan_urlallScan any public URL, or a registered site for full tracking (Pro+).
check_pdfallRun a PDF/UA-1 structure check on a public PDF.
get_scan · get_findingsallRead a scan_url scan's status, severity counts, and findings — either kind, recorded or one-off.
list_sitesPro+List the account's registered sites.
scan_sitePro+Crawl and scan every reachable page of a registered site.
get_run · get_run_findingsPro+Read a full-site run from scan_site.
get_root_causesPro+Group a run's repeated DOM patterns and return factual element/page blast radius.
run_journeyPro+Replay a saved multi-step journey and check each step.
get_trendsPro+Read a site's violation-count history over time.

One id, one poll tool: whatever scan_url did with a URL, get_scan and get_findings read it back. get_run and get_run_findings are only for full-site runs from scan_site.

Every scan-producing tool returns the coverage disclaimer in both the text content and the structured content. There is no score, grade, or conformance verdict — automated testing finds roughly 30–57% of accessibility issues, and the remainder needs manual review.

Configuration

Env varUsed byMeaning
WCAGC_API_BASE_URLbothThe wcagc API to call. Defaults to https://api.wcagc.com; set it only when self-hosting.
WCAGC_MCP_KEYstdioYour mcp:scan API key.
PORThostedPort to listen on (default 8080).
WCAGC_MCP_ALLOWED_HOSTShostedComma-separated Host-header allowlist (DNS-rebinding protection when bound to 0.0.0.0).
WCAGC_MCP_INTROSPECT_TTL_SECONDShostedHow long a verified bearer is cached before re-checking with the API (default 60).
WCAGC_MCP_OAUTH_ISSUERhostedExpected OAuth issuer (defaults to WCAGC_API_BASE_URL).
WCAGC_MCP_OAUTH_JWKS_URLhostedAuthorization Server public JWKS URL.
WCAGC_MCP_URLhostedCanonical RFC 9728 protected-resource URL (defaults to https://mcp.wcagc.com/mcp).
WCAGC_MCP_JWKS_TTL_SECONDShostedJWKS cache TTL; an unknown kid triggers an immediate refetch.
WCAGC_OPENAI_APPS_CHALLENGEhostedOpenAI Plugins Directory domain-verification token; keep it in the deployment secret store, never in source.

Development

Hosted HTTP requests to /mcp and discovery endpoints produce JSON logs with a generated request ID, HTTP status, MCP method, error code and duration. Tokens, headers, query strings, tool arguments and results are excluded. Health probes are not logged.

The Docker entrypoint preloads the New Relic ESM agent. Set NEW_RELIC_AGENT_ENABLED=true, NEW_RELIC_APP_NAME=wcagc-mcp and the deployment secret NEW_RELIC_LICENSE_KEY to enable APM and forwarding of these safe request logs. The license key must belong to the existing New Relic account; never commit it. The stdio entrypoint does not load the agent.

npm install
npm run dev        # hosted, watch mode
npm run start:stdio # stdio mode
npm run typecheck
npm run verify      # node:test against a local fixture API

License

MIT — see LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.