Checks if an SQL query can be executed and rolls back afterward.
AI agents invoke test_execute to trigger actions in MySQL 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.
Although the rollback prevents permanent data changes, the tool still executes arbitrary SQL statements against the database. This includes potentially expensive or disruptive queries (e.g., full table scans, locks, DDL statements that may not be fully rollback-safe). The execution of arbitrary SQL places it in the Execute category.
From the tool's definition 'Checks if an SQL query can be executed and rolls back afterward' — the tool actually executes arbitrary SQL but rolls back the transaction, meaning it runs code with transactional side effects that are then reversed.
Documented attack patterns abuse exactly the kind of access test_execute gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MySQL MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for test_execute:
{
"version": "1",
"default": "deny",
"tools": {
"test_execute": {
"limits": [
{
"counter": "test_execute_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}test_execute 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.
Checks if an SQL query can be executed and rolls back afterward. It is categorised as a Execute tool in the MySQL MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MySQL MCP Server MCP server in PolicyLayer and add a rule for test_execute: 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 MySQL MCP Server. Nothing to install.
test_execute 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 test_execute 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 test_execute. 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.
test_execute is provided by the MySQL MCP Server MCP server (xiangma9712/mysql-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MySQL 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.
4 MySQL MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.