evaluate_verification
Roll up a per-SC verification verdict from the checks you have resolved. Pass the verification predicate ids you confirmed as pass and fail; anything unresolved stays UNVERIFIED — never assumed to pass. Returns pass / fail / unverified per SC. This is a status report, NOT a conformance claim.
This record as markdown: /tools/a11y-assist-mcp/evaluate-verification.md
What evaluate_verification does on A11y Assist
AI agents call evaluate_verification to retrieve information from A11y Assist without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
scs | array | Yes | Applicable SC ids to roll up (from evaluate_applicability). |
fail | array | — | Verification predicate ids confirmed NOT to hold (violations). |
pass | array | — | Verification predicate ids confirmed to HOLD — from axe passing (audit_html), your inspection of the markup, or the user confirming. |
Parameters from the server's own tool schema.
Why evaluate_verification is rated Low
Even though evaluate_verification only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs evaluate_verification 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_verification, this is the rule to start with:
evaluate_verification is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect A11y Assist, apply this rule, and every evaluate_verification call is checked against it from then on.
Questions about evaluate_verification
Roll up a per-SC verification verdict from the checks you have resolved. Pass the verification predicate ids you confirmed as pass and fail; anything unresolved stays UNVERIFIED — never assumed to pass. Returns pass / fail / unverified per SC. This is a status report, NOT a conformance claim. It is categorised as a Read tool in the A11y Assist MCP Server, which means it retrieves data without modifying state.
evaluate_verification accepts 3 parameters: scs, fail, pass. Required: scs. The full parameter table on this page comes from the server's own tool schema.
Register the A11y Assist MCP server in PolicyLayer and add a rule for evaluate_verification: 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.
evaluate_verification 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 evaluate_verification 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 evaluate_verification. 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.
evaluate_verification 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.
More on A11y Assist, and thousands of servers like it.
This server
Across the catalogue