MCP server

The Accessibility Company exposes a Model Context Protocol (MCP) endpoint so AI coding agents can:

• read your open accessibility issues,
• fetch the selector / failing HTML for a specific issue,
• mark issues as in progress or as inspected-and-dismissed (false positive / by design),
• and verify a fix against one URL in under 30 seconds.

The server is hosted at mcp.theaccessibility.company and speaks the MCP spec version 2025-03-26 over Streamable HTTP.

Compatible clients: Cursor, Claude Code, Codex CLI, and Factory Droid.

1 — Create a token

Sign in to the dashboard and open Settings → Integrations → MCP tokens. Click Create token and choose:

Field	Recommendation
Name	Something descriptive — e.g. My laptop / Cursor or CI bot.
Scope	Read-only to start. Upgrade to Read + write once you’re sure you want the agent marking issues / running verify scans.
Site scope	Account-wide for general use; pick a site if the agent should only see one project.
Expiry	Leave blank, or set 30–90 days for laptop tokens you want to rotate.

Tokens begin with the prefix tac_mcp_ and are 32 hex characters of entropy. They are shown exactly once — copy the token from the success dialog and paste it into your MCP client immediately.

Only owners and admins can manage MCP tokens.

Same token, two surfaces

The same token also authenticates the read-only REST API.

2 — Wire the token into your client

The token goes in the Authorization header as Bearer tac_mcp_<your-32-hex>. Each client formats this slightly differently.

Cursor

// .cursor/mcp.json (project) or ~/.cursor/mcp.json (global)
{
  "mcpServers": {
    "tac": {
      "url": "https://mcp.theaccessibility.company/mcp",
      "headers": {
        "Authorization": "Bearer tac_mcp_..."
      }
    }
  }
}

Claude Code

claude mcp add --transport http tac \
  https://mcp.theaccessibility.company/mcp \
  --header "Authorization: Bearer tac_mcp_..."

Codex CLI

~/.codex/config.toml

[mcp_servers.tac]
url = "https://mcp.theaccessibility.company/mcp"
headers = { Authorization = "Bearer tac_mcp_..." }

Factory Droid

droid mcp add tac https://mcp.theaccessibility.company/mcp \
  --type http \
  --header "Authorization: Bearer tac_mcp_..."

After adding the server, restart your agent so it re-runs initialize + tools/list.

3 — Available tools

Tool	Scope	What it does
tac.listSites	read	Sites in the account (or just the one if site-scoped) with open / critical / serious issue counts.
tac.listOpenIssues	read	Ranked list of actionable issues. Filters: siteId, ruleId, minImpact, limit, offset.
tac.getIssueWithFixContext	read	One issue + rule help URL + representative finding (selector, HTML snippet, failure summary) + affected pages + verify hint + agent memory. aiContext carries any dashboard-generated AI summary and before/after fix suggestion; findingsLimit > 0 adds every occurrence’s selector + snippet for template bugs.
tac.getDecisions	read	The workspace’s accumulated judgement: active ignore ledger + recently-reported fixes. Read this first.
tac.getComplianceChecklist	read	Per-criterion WCAG checklist state (combined auto + human verdicts) with a progress rollup. Filter by status to pull just failing / needs-review rows.
tac.markIssueInProgress	write	Flip status to in_progress and record an optional note on the activity timeline.
tac.markIssueFixed	write	Flip status to fixed_pending_verification after a fix lands (ideally after a passing verify). Only a full re-scan moves an issue to verified — agents can never self-certify.
tac.markIssueIgnored	write	Persist an issue-level ignore on rule_id + selector_pattern. Reason required; expiry capped at one year out.
tac.verifyFixAtUrl	write	Run one synchronous scan and return the identity-hash delta + whether the issue’s rule still fires. Rate limited to 10/min/token.

tac.* tools all return structured JSON results inside an MCP tools/call envelope. Error codes follow the dispatch contract (MISSING_TOKEN, INSUFFICIENT_SCOPE, SITE_SCOPE_MISMATCH, NOT_FOUND, INVALID_INPUT, RATE_LIMITED, INTERNAL_ERROR).

Prompts

The server also exposes MCP prompts — invoke them from your client’s prompt picker:

Prompt	Arguments	What it does
fix-next-issue	siteId?, issueKey?	Runs the full remediation loop: decisions → pick issue → fix context → code change → verify → record the fix with provenance.
compliance-status-report	siteId	Read-only: gathers checklist + open-issue data and writes a grounded compliance posture report.

4 — Security model

The server enforces defence in depth:

1. Transport. TLS terminated at the Cloudflare edge.
2. Authentication. Every JSON-RPC tools/call must include a valid Authorization: Bearer tac_mcp_<32hex> header. The token is hashed with SHA-256 and looked up server-side; plaintext is never stored.
3. Site scope. Tokens may be locked to a single site; any tool call that references a different site returns SITE_SCOPE_MISMATCH. For tools that don’t take a siteId, the site is resolved from the issue record and the check is enforced server-side.
4. Account isolation. All reads are scoped to your account; cross-account leakage is structurally impossible.
5. URL guards (verifyFixAtUrl). URLs must be http(s), their hostname must match the site’s base hostname, and private / loopback / link-local addresses are rejected outright.
6. Scope checks. Each tool declares required scopes; tokens lacking the scope return INSUFFICIENT_SCOPE.
7. Audit log. Every successful tool call writes an audit event with the actor, the tool name, the redacted input, and the token id.
8. Owner/admin token creation. Only account owners and admins can mint MCP tokens.

Token rotation from Settings → Integrations is immediate — revoked tokens fail within ~100 ms.

5 — The verify-fix loop

The packaged fix-next-issue MCP prompt runs this loop for you; the manual version using the tools directly:

1. tac.getDecisions — respect prior by-design / false-positive / wont-fix decisions before doing anything.
2. tac.listOpenIssues — pick the highest-priority issue.
3. tac.getIssueWithFixContext({ issueKey }) — read the rule help URL, the representative finding’s selector + HTML snippet, the failing pages, and any aiContext fix suggestion.
4. tac.markIssueInProgress({ issueKey, note }) — flip status.
5. Write the fix.
6. tac.verifyFixAtUrl({ issueKey }) against one affected URL.
7. Inspect expectedFixedSummary.persists:
   • false — the rule no longer fires; call tac.markIssueFixed({ issueKey, fixedBy }) with PR / commit provenance and hand off for the full-site re-scan.
   • true — the fix didn’t take; iterate from step 5.

A full-site re-scan is still required to clear all affected pages — kick that off from the dashboard once the representative URL is clean.

6 — Troubleshooting

Symptom	Likely cause	Fix
MISSING_TOKEN	The client is calling /mcp without the Authorization header.	Re-check the client config snippet. Many clients require restart after editing the file.
MALFORMED_TOKEN	Token doesn’t begin with tac_mcp_ or is the wrong length.	You probably pasted a webhook token by mistake. Mint a fresh MCP token from Settings → Integrations.
TOKEN_REVOKED / TOKEN_EXPIRED	Self-explanatory.	Mint a new token.
SITE_SCOPE_MISMATCH	Token is locked to one site, but the tool call referenced another site.	Either retarget the call to the locked site, or mint an account-wide token.
RATE_LIMITED	verifyFixAtUrl token has hit 10 calls / minute.	Wait — the limit resets on a sliding window. Don’t loop on failed verifies.
/mcp returns 405 on GET	Expected. v1 is Streamable HTTP only.	Use a client that supports Streamable HTTP (all four clients above do).

7 — Privacy

Tool inputs are persisted to the audit log for traceability. Long URLs (>256 chars) and long reason strings (>512 chars) are truncated server-side before logging. Token plaintext is never stored or logged — only the SHA-256 hash and the eight-char prefix.