AI agents invoke runApp to trigger actions in YingDao RPA MCP 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.
This tool executes applications via the RPA automation platform, which qualifies as Execute (triggers external operations whose effects depend on arguments). Severity is high due to the broad potential impact—running arbitrary applications could affect system state, modify data, or trigger unintended side effects.
From the tool's definition Tool name 'runApp' combined with server description indicating 'automated execution of repetitive tasks' and context of RPA capabilities. The tool enables running applications through the RPA system. Description is empty, reducing certainty slightly.
Documented attack patterns abuse exactly the kind of access runApp gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and YingDao RPA MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for runApp:
{
"version": "1",
"default": "deny",
"tools": {
"runApp": {
"limits": [
{
"counter": "runapp_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}runApp 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.
runApp. It is categorised as a Execute tool in the YingDao RPA MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the YingDao RPA MCP Server MCP server in PolicyLayer and add a rule for runApp: 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 YingDao RPA MCP Server. Nothing to install.
runApp 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 runApp 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 runApp. 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.
runApp is provided by the YingDao RPA MCP Server MCP server (ying-dao/yingdao_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 YingDao RPA MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 YingDao RPA MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.