AI agents invoke execute-prepared-query to trigger actions in Consul 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 triggers execution of arbitrary pre-stored query logic in Consul. While not as severe as arbitrary code execution or data destruction, it can modify system state, trigger cascading operations, or extract sensitive information depending on the prepared query's definition. The blast radius depends on what the prepared query does, making it an Execute-category risk.
From the tool's definition Tool name 'execute-prepared-query' and description 'Execute a prepared query' indicate execution of pre-stored query logic.
Documented attack patterns abuse exactly the kind of access execute-prepared-query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Consul MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute-prepared-query:
{
"version": "1",
"default": "deny",
"tools": {
"execute-prepared-query": {
"limits": [
{
"counter": "execute-prepared-query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute-prepared-query 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 prepared query. It is categorised as a Execute tool in the Consul MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Consul MCP Server MCP server in PolicyLayer and add a rule for execute-prepared-query: 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 Consul MCP Server. Nothing to install.
execute-prepared-query 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-prepared-query 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-prepared-query. 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-prepared-query is provided by the Consul MCP Server MCP server (kocierik/consul-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Consul 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.
25 Consul MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.