// MCP TOOL REFERENCE

pilot_drag

ServerPilot
CategoryExecute

WHAT PILOT_DRAG ON PILOT DOES

AI agents invoke pilot_drag to trigger actions in Pilot. 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.

THE RISK

High Risk

This tool performs a browser action (drag and drop) in a persistent Chromium session. It executes UI interactions that can reorder items, move elements, or trigger application-level side effects depending on the target page. It's not purely destructive or financial, but it is an external operation whose effects depend on arguments and page context, placing it firmly in Execute.

From the tool's definition 'Drag one element and drop it onto another element on the page' — triggers a browser interaction (drag-and-drop) that manipulates UI state in a live Chromium instance

Documented attack patterns abuse exactly the kind of access pilot_drag gives an agent:

HOW TO CONTROL PILOT_DRAG

PolicyLayer is an MCP gateway — it sits between your AI agents and Pilot, and nothing reaches the server without passing your rules. This is the rule we recommend for pilot_drag:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "pilot_drag": {
      "limits": [
        {
          "counter": "pilot_drag_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

pilot_drag stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

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

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

More Pilot tools

Destructive pilot_geolocation Set or clear the browser Execute pilot_frame_reset Switch the browser context back to the main page frame after working inside an iframe. Use Execute pilot_reload Reload the current page, waiting for DOM content to load. Use when the user wants to refre Execute pilot_evaluate Execute a JavaScript expression or function in the browser page context and return the res Execute pilot_hover Hover the mouse over an element, triggering hover states, tooltips, and dropdown menus. Us Execute pilot_intercept Intercept network requests matching a URL pattern and respond with custom status, headers, Execute pilot_navigate Navigate the browser to a URL and wait for DOM content to load. Use when the user wants to Execute pilot_tab_new Open a new browser tab, optionally navigating to a URL. Use when the user wants to open a

All 61 Pilot tools →

Execute tools on other servers

Frida Game Hacking MCP remove_breakpoint Procmon request_elevation WireMCP capture_packets Pentest Ai run_probe

Go deeper

High-risk tools in Pilot → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

What does the pilot_drag tool do? +

Drag one element and drop it onto another element on the page. Use when the user wants to move an element, reorder items in a drag-and-drop list, or interact with a drag-and-drop UI. Parameters: - start_ref: The source element reference from snapshot (e.g.,. It is categorised as a Execute tool in the Pilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on pilot_drag? +

Register the Pilot MCP server in PolicyLayer and add a rule for pilot_drag: 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 Pilot. Nothing to install.

What risk level is pilot_drag? +

pilot_drag is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit pilot_drag? +

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

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

pilot_drag is provided by the Pilot MCP server (tacosyhorchata/pilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Pilot tool call.

Deterministic rules across all 61 Pilot tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN PILOT →

Free to start. No card required.

61 Pilot tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

pilot_drag

// WHAT PILOT_DRAG ON PILOT DOES

// THE RISK

// HOW TO CONTROL PILOT_DRAG

// EXPLORE