sp_a11y

THE RISK

High Risk

Why sp_a11y needs a policy

The tool executes an accessibility audit process and automatically applies fixes to HTML (modifying contrast, semantics, ARIA attributes, and touch targets). This constitutes code execution with side effects on document structure and styling. While the fixes are reversible and beneficial, the tool triggers automated modifications whose specific effects depend on the input HTML analyzed.

From the tool's definition Tool description states 'Run WCAG 2.1 AA accessibility audit on HTML and auto-fix issues' — the verbs 'run' and 'auto-fix' indicate execution of code/operations that modify HTML content.

Documented attack patterns abuse exactly the kind of access sp_a11y gives an agent:

POLICY

How to control sp_a11y

PolicyLayer is an MCP gateway — it sits between your AI agents and Stitch Pro, and nothing reaches the server without passing your rules. This is the rule we recommend for sp_a11y:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sp_a11y": {
      "limits": [
        {
          "counter": "sp_a11y_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

sp_a11y stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Stitch Pro — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Stitch Pro tools

Execute sp_auto Describe what you want in plain English. Automatically chains design system creation, page Execute sp_to_svelte Convert HTML/Tailwind to SvelteKit components with Svelte 5 runes ($state) and optional co Execute sp_to_vue Convert HTML/Tailwind to Vue 3 Single File Components with Composition API and optional co Execute sp_smart_convert Converts HTML to a framework, but auto-detects if it needs accessibility fixes and respons Write sp_flow Generate multiple related screens (e.g., login → dashboard → settings) in one call with co Write sp_responsive Make HTML responsive by injecting Tailwind breakpoints for mobile, tablet, and desktop Write sp_to_react Convert HTML/Tailwind to Next.js/React components with proper state, props, hooks, and opt Write sp_create_project Create a new Stitch project. Returns the project ID needed for sp_generate and sp_auto.

All 17 Stitch Pro tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Stitch Pro → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about sp_a11y

What does the sp_a11y tool do? +

Run WCAG 2.1 AA accessibility audit on HTML and auto-fix issues (contrast, semantics, ARIA, touch targets). It is categorised as a Execute tool in the Stitch Pro MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on sp_a11y? +

Register the Stitch Pro MCP server in PolicyLayer and add a rule for sp_a11y: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Stitch Pro. Nothing to install.

What risk level is sp_a11y? +

sp_a11y is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit sp_a11y? +

Yes. Add a rate_limit block to the sp_a11y rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block sp_a11y completely? +

Set action: deny in the PolicyLayer policy for sp_a11y. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides sp_a11y? +

sp_a11y is provided by the Stitch Pro MCP server (luciferdono/stitch-pro-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Stitch Pro tool call.

Start from Stitch Pro, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →