AI agents invoke execute_api to trigger actions in ZStack 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.
ZStack is a cloud infrastructure platform. An execute_api tool with no constraints documented can trigger any of 2000+ cloud APIs, which could include resource creation, modification, deletion, or control operations. While the tool name alone is 'execute', the context of ZStack Cloud APIs—which almost certainly include destructive and financial operations—means misuse could have severe consequences.
From the tool's definition Tool named 'execute_api' in a server that 'execute[s] 2000+ ZStack Cloud APIs'. The verb 'execute' combined with the scope of 2000+ cloud APIs indicates the tool triggers external operations whose effects depend on arguments.
Documented attack patterns abuse exactly the kind of access execute_api gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ZStack MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_api:
{
"version": "1",
"default": "deny",
"tools": {
"execute_api": {
"limits": [
{
"counter": "execute_api_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_api 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.
execute_api. It is categorised as a Execute tool in the ZStack MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ZStack MCP Server MCP server in PolicyLayer and add a rule for execute_api: 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 ZStack MCP Server. Nothing to install.
execute_api 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 execute_api 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 execute_api. 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.
execute_api is provided by the ZStack MCP Server MCP server (zstackio/zstack-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ZStack MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 ZStack MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.