AI agents invoke execute-tool to trigger actions in MCP Create 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 triggers execution of unspecified tools on spawned MCP servers. The effects depend entirely on which tool is executed and its arguments. While not inherently destructive or financial, execution of arbitrary tools presents high risk because: (1) an AI agent could execute tools with unintended side effects, (2) the blast radius depends on what tools exist on the target server, and (3) combined with sibling…
From the tool's definition Tool name is 'execute-tool' and description states it will 'Execute a tool on a server'. This directly indicates execution of arbitrary tools on MCP servers.
Documented attack patterns abuse exactly the kind of access execute-tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Create Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute-tool:
{
"version": "1",
"default": "deny",
"tools": {
"execute-tool": {
"limits": [
{
"counter": "execute-tool_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute-tool 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 a tool on a server. It is categorised as a Execute tool in the MCP Create Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Create Server MCP server in PolicyLayer and add a rule for execute-tool: 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 Create Server. Nothing to install.
execute-tool 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-tool 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-tool. 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-tool is provided by the MCP Create Server MCP server (tesla0225/mcp-create). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 MCP Create Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 MCP Create Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.