# browser_drag

Perform drag and drop between two elements

Agent View of the PolicyLayer registry record for `browser_drag`. HTML page: https://policylayer.com/tools/a11y-agent-skills/browser-drag

## Facts

- Tool: `browser_drag`
- Server: A11y Agent Skills (`smukh/a11y-agent-skills`) — https://policylayer.com/tools/a11y-agent-skills.md
- Homepage: https://github.com/smukh/a11y-agent-skills
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

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

## Why browser_drag is rated High

Drag and drop is a browser action that causes external side effects depending on arguments (e.g., reordering items, moving files, triggering drop events). It does not merely read data, and its effects vary widely based on context. It fits the Execute category as it triggers an external UI operation whose outcome depends on which elements are targeted.

From the tool's own definition: "'Perform drag and drop between two elements' — triggers a browser interaction that manipulates UI state"

## Use case

AI agents invoke browser_drag to trigger actions in A11y Agent Skills. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_drag": {
      "limits": [
        {
          "counter": "browser_drag_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on A11y Agent Skills (23)

- `browser_click` — Execute — https://policylayer.com/tools/a11y-agent-skills/browser-click.md
- `browser_fill_form` — Execute — https://policylayer.com/tools/a11y-agent-skills/browser-fill-form.md
- `browser_hover` — Execute — https://policylayer.com/tools/a11y-agent-skills/browser-hover.md
- `browser_navigate` — Execute — https://policylayer.com/tools/a11y-agent-skills/browser-navigate.md
- `browser_press_key` — Execute — https://policylayer.com/tools/a11y-agent-skills/browser-press-key.md
- `browser_select_option` — Execute — https://policylayer.com/tools/a11y-agent-skills/browser-select-option.md
- `browser_set_checked` — Execute — https://policylayer.com/tools/a11y-agent-skills/browser-set-checked.md
- `browser_type` — Execute — https://policylayer.com/tools/a11y-agent-skills/browser-type.md
- `run_keyboard_journey` — Execute — https://policylayer.com/tools/a11y-agent-skills/run-keyboard-journey.md
- `scan_page` — Execute — https://policylayer.com/tools/a11y-agent-skills/scan-page.md
- `verify_repair` — Execute — https://policylayer.com/tools/a11y-agent-skills/verify-repair.md
- `browser_expect_list_visible` — Read — https://policylayer.com/tools/a11y-agent-skills/browser-expect-list-visible.md
- `browser_snapshot` — Read — https://policylayer.com/tools/a11y-agent-skills/browser-snapshot.md
- `get_rule_help` — Read — https://policylayer.com/tools/a11y-agent-skills/get-rule-help.md
- `scan_html` — Read — https://policylayer.com/tools/a11y-agent-skills/scan-html.md
- `browser_expect_title` — Write — https://policylayer.com/tools/a11y-agent-skills/browser-expect-title.md
- `browser_expect_url` — Write — https://policylayer.com/tools/a11y-agent-skills/browser-expect-url.md
- `browser_expect_value` — Write — https://policylayer.com/tools/a11y-agent-skills/browser-expect-value.md
- `browser_expect_visible` — Write — https://policylayer.com/tools/a11y-agent-skills/browser-expect-visible.md
- `browser_expect_visible_text` — Write — https://policylayer.com/tools/a11y-agent-skills/browser-expect-visible-text.md
- `compare_reports` — Write — https://policylayer.com/tools/a11y-agent-skills/compare-reports.md
- `refuse_to_perform` — Write — https://policylayer.com/tools/a11y-agent-skills/refuse-to-perform.md
- `report_result` — Write — https://policylayer.com/tools/a11y-agent-skills/report-result.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-skills · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a11y-agent-skills