evaluate_applicability

SERVERA11y Assist SOURCEa11y-assist-mcp

Medium RISK CLASS

Category Write

Parameters 60 required

Recommended Rate-limitedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/a11y-assist-mcp/evaluate-applicability.md

WHAT IT DOES

What evaluate_applicability does on A11y Assist

AI agents use evaluate_applicability to create or update resources in A11y Assist, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your A11y Assist environment.

Parameter	Type	Required	Description
`role`	string	—	ARIA role of a primitive, e.g. textbox. Provide this OR pattern.
`level`	string	—	Conformance level (cumulative).
`facets`	array	—	Facet keys your component involves (from the facet-gates step), e.g. ["color-contrast","text-language"]. Returns the subgate questions under only those facets.
`pattern`	string	—	APG pattern name, e.g. accordion. Provide this OR role.
`present`	array	—	Applicability predicate ids that hold for YOUR specific component (its content / context). Provide on the final call to get the complete applicable SC set + che
`subgates`	array	—	Subgate ids your component involves (from the subgates step), e.g. ["color-contrast\|0"]. Returns the leaf predicate questions under only those subgates.

Parameters from the server's own tool schema.

RISK

Why evaluate_applicability is rated Medium

An AI agent can call evaluate_applicability faster than any human can review: one bad instruction and it creates or modifies resources in A11y Assist by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs evaluate_applicability safely

PolicyLayer is an MCP gateway: it sits between your AI agents and A11y Assist, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For evaluate_applicability, this is the rule to start with:

evaluate_applicability Rate-limited

evaluate_applicability stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "evaluate_applicability": {
      "limits": [
        {
          "counter": "evaluate_applicability_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect A11y Assist, apply this rule, and every evaluate_applicability call is checked against it from then on.

FAQ

Questions about evaluate_applicability

What does the evaluate_applicability tool do? +

REFINE the applicable WCAG criteria for a component beyond the structural floor that get_apg_pattern / get_aria_role return. Gate-first walkthrough — the same engine the website uses — that prunes the question set to only what your component can be affected by. Four steps: (1) pattern|role + level, nothing else → the coarse facet gates ("Any audio or video?"); (2) facets = the keys that apply → the subgates (finer questions) under them; (3) subgates = the ids that apply → the leaf predicates (yes/no on your content); (4) present = the predicate ids that hold → the COMPLETE applicable SC set + a tiered verification checklist. You can also jump straight to step 4 with present if you already know which predicates hold. Then resolve the checklist (audit_html for axe, inspect markup for the agent tier, ask the user for the human tier) and roll it up with evaluate_verification. It is categorised as a Write tool in the A11y Assist MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does evaluate_applicability accept? +

evaluate_applicability accepts 6 parameters: role, level, facets, pattern, present, subgates. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on evaluate_applicability? +

Register the A11y Assist MCP server in PolicyLayer and add a rule for evaluate_applicability: 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 A11y Assist. Nothing to install.

What risk level is evaluate_applicability? +

evaluate_applicability is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit evaluate_applicability? +

Yes. Add a rate_limit block to the evaluate_applicability 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 evaluate_applicability completely? +

Set action: deny in the PolicyLayer policy for evaluate_applicability. 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 evaluate_applicability? +

evaluate_applicability is provided by the A11y Assist MCP server (a11y-assist-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on A11y Assist, and thousands of servers like it.

This server

All 12 A11y Assist tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →