get-criteria-by-level

THE RISK

Low Risk

Why get-criteria-by-level needs a policy

This is a straightforward data retrieval tool that queries the WCAG 2.2 guidelines database and returns success criteria matching specified conformance levels (A, AA, AAA). No side effects occur—it does not create, modify, delete, or execute external operations. This is categorized as Read per the classification rules for tools that retrieve or query data without side effects.

From the tool's definition Tool performs a query/retrieval operation: 'Gets all success criteria for a specific conformance level.' Returns WCAG guideline data without modifying, deleting, or executing any operations.

Documented attack patterns abuse exactly the kind of access get-criteria-by-level gives an agent:

POLICY

How to control get-criteria-by-level

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 get-criteria-by-level:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get-criteria-by-level": {}
  }
}

get-criteria-by-level is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

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

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More WCAG MCP Server tools

Read whats-new-in-wcag22 Lists all success criteria that were added in WCAG 2.2. Read count-criteria Returns counts of success criteria grouped by level, principle, or guideline. Read get-criterion Gets full details for a specific WCAG success criterion by its reference number (e.g., Read get-failures-for-criterion Gets failure techniques (common mistakes) for a specific success criterion. Read get-full-criterion-context Gets comprehensive context for a success criterion including techniques, test rules, and r Read get-glossary-term Gets the definition of a WCAG glossary term. Read get-guideline Gets full details for a specific WCAG guideline including all its success criteria. Read get-server-info Returns information about this WCAG MCP server and data source.

All 20 WCAG MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get-criteria-by-level

What does the get-criteria-by-level tool do? +

Gets all success criteria for a specific conformance level. Optionally includes lower levels (e.g., AA includes A). It is categorised as a Read tool in the WCAG MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get-criteria-by-level? +

Register the WCAG MCP Server MCP server in PolicyLayer and add a rule for get-criteria-by-level: 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.

What risk level is get-criteria-by-level? +

get-criteria-by-level is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get-criteria-by-level? +

Yes. Add a rate_limit block to the get-criteria-by-level 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 get-criteria-by-level completely? +

Set action: deny in the PolicyLayer policy for get-criteria-by-level. 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 get-criteria-by-level? +

get-criteria-by-level 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.

Enforce policy on every WCAG MCP Server tool call.

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.

CHECK YOUR STACK →