AI agents invoke close-appium to trigger actions in MCP Appium Server. 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.
Closing an Appium driver session terminates an active automation session and disconnects from the device. This is an external operation that ends a running process/connection. It's reversible (a new session can be started), so it's not Destructive, but it does trigger an external side effect beyond simple data reads or writes, placing it in Execute. Misuse could disrupt ongoing automation workflows.
From the tool's definition Close the current Appium driver session
Documented attack patterns abuse exactly the kind of access close-appium gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Appium Server, and nothing reaches the server without passing your rules. This is the rule we recommend for close-appium:
{
"version": "1",
"default": "deny",
"tools": {
"close-appium": {
"limits": [
{
"counter": "close-appium_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}close-appium 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.
Close the current Appium driver session. It is categorised as a Execute tool in the MCP Appium Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Appium Server MCP server in PolicyLayer and add a rule for close-appium: 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 MCP Appium Server. Nothing to install.
close-appium 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 close-appium 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 close-appium. 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.
close-appium is provided by the MCP Appium Server MCP server (rahulec08/appium-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 110 MCP Appium Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
110 MCP Appium Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.