AI agents invoke execute_sql_query to trigger actions in Text-to-SQL 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 arbitrary SQL queries, which can trigger complex database operations with side effects depending on the query arguments. While the server description mentions 'permission management and security controls,' the tool itself performs code execution (SQL) whose effects are data-dependent and potentially irreversible if the query includes DELETE, DROP, UPDATE, or other destructive statements.
From the tool's definition Tool name 'execute_sql_query' combined with description '执行SQL查询' (Execute SQL query in Chinese) indicates the tool runs SQL commands against a database.
Documented attack patterns abuse exactly the kind of access execute_sql_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Text-to-SQL MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_sql_query:
{
"version": "1",
"default": "deny",
"tools": {
"execute_sql_query": {
"limits": [
{
"counter": "execute_sql_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_sql_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.
执行SQL查询. It is categorised as a Execute tool in the Text-to-SQL MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Text-to-SQL MCP Server MCP server in PolicyLayer and add a rule for execute_sql_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 Text-to-SQL MCP Server. Nothing to install.
execute_sql_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_sql_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_sql_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_sql_query is provided by the Text-to-SQL MCP Server MCP server (tmstack/text-to-sql-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Text-to-SQL 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.
5 Text-to-SQL MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.