Returns counts of success criteria grouped by level, principle, or guideline.
AI agents call count-criteria to retrieve information from WCAG MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query tool that retrieves and aggregates existing WCAG data without side effects. It cannot create, modify, delete, execute code, or trigger external operations. The result is purely informational counts used for analysis or navigation of the WCAG guidelines database. There is no blast radius from misuse—an AI agent requesting criteria counts poses no security or operational risk.
From the tool's definition Tool returns counts/aggregations of success criteria grouped by various dimensions (level, principle, guideline).
Documented attack patterns abuse exactly the kind of access count-criteria gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and WCAG MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for count-criteria:
{
"version": "1",
"default": "deny",
"tools": {
"count-criteria": {}
}
}count-criteria is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Returns counts of success criteria grouped by level, principle, or guideline. It is categorised as a Read tool in the WCAG MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WCAG MCP Server MCP server in PolicyLayer and add a rule for count-criteria: 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 WCAG MCP Server. Nothing to install.
count-criteria is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the count-criteria 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.
Set action: deny in the PolicyLayer policy for count-criteria. 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.
count-criteria is provided by the WCAG MCP Server MCP server (joe-watkins/wcag-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from WCAG MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
20 WCAG MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.