AI agents invoke drag_drop to trigger actions in OpenChrome. 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.
This tool performs a browser UI action (drag and drop) in a real Chrome browser. It executes an interaction that can move elements, reorder items, upload files, or trigger other UI-driven operations whose effects depend on arguments. This is an Execute-category action; severity is medium because misuse could rearrange or manipulate UI state, though effects are generally reversible.
From the tool's definition Drag and drop by selector or coordinates — triggers browser interaction/action on real Chrome browser
Documented attack patterns abuse exactly the kind of access drag_drop gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenChrome, and nothing reaches the server without passing your rules. This is the rule we recommend for drag_drop:
{
"version": "1",
"default": "deny",
"tools": {
"drag_drop": {
"limits": [
{
"counter": "drag_drop_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}drag_drop 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.
Free to start. No card required.
Drag and drop by selector or coordinates. Pass intent=. It is categorised as a Execute tool in the OpenChrome MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenChrome MCP server in PolicyLayer and add a rule for drag_drop: 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 OpenChrome. Nothing to install.
drag_drop is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the drag_drop 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 drag_drop. 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.
drag_drop is provided by the OpenChrome MCP server (shaun0927/openchrome). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 106 OpenChrome tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
106 OpenChrome tools catalogued and risk-classified — across an index of 42,500+ MCP servers.