# compare_reports

Classify new, resolved, unchanged, and changed-or-uncertain findings in two audit reports.

Agent View of the PolicyLayer registry record for `compare_reports`. HTML page: https://policylayer.com/tools/a11y-agent-mcp/compare-reports

## Facts

- Tool: `compare_reports`
- Server: A11y Agent (`@a11y-agent/mcp`) — https://policylayer.com/tools/a11y-agent-mcp.md
- Install: `npx -y @a11y-agent/mcp`
- Homepage: https://www.npmjs.com/package/@a11y-agent/mcp
- Risk category: Read (Low risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 2 (2 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `after` | object | yes |  |
| `before` | object | yes |  |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "compare_reports",
    "arguments": {
      "after": {},
      "before": {}
    }
  }
}
```

## Why compare_reports is rated Low

Even though compare_reports 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.

Risk signals: High parameter count (108 properties)

## Use case

AI agents call compare_reports to retrieve information from A11y Agent without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches A11y Agent:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "compare_reports": {}
  }
}
```

## Other tools on A11y Agent (5)

- `run_keyboard_journey` — Execute — https://policylayer.com/tools/a11y-agent-mcp/run-keyboard-journey.md
- `scan_page` — Execute — https://policylayer.com/tools/a11y-agent-mcp/scan-page.md
- `verify_repair` — Execute — https://policylayer.com/tools/a11y-agent-mcp/verify-repair.md
- `get_rule_help` — Read — https://policylayer.com/tools/a11y-agent-mcp/get-rule-help.md
- `scan_html` — Read — https://policylayer.com/tools/a11y-agent-mcp/scan-html.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=a11y-agent-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a11y-agent-mcp