Execute SQL query on a SkySQL database instance and return the results
AI agents invoke execute_sql to trigger actions in Skysql. 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 runs arbitrary SQL code against a live database. While not inherently destructive (unlike delete_db), it enables execution of potentially harmful operations (data modification, schema deletion) depending on the query passed by the agent. This makes it Execute rather than Write, as the blast radius is determined by the power of SQL itself.
From the tool's definition "Execute SQL query" on a database instance. SQL queries can include SELECT, UPDATE, DELETE, DROP, and other operations whose effects depend entirely on the query argument provided.
Documented attack patterns abuse exactly the kind of access execute_sql gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Skysql, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_sql:
{
"version": "1",
"default": "deny",
"tools": {
"execute_sql": {
"limits": [
{
"counter": "execute_sql_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_sql 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 SQL query on a SkySQL database instance and return the results. It is categorised as a Execute tool in the Skysql MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Skysql MCP server in PolicyLayer and add a rule for execute_sql: 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 Skysql. Nothing to install.
execute_sql 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 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. 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 is provided by the Skysql MCP server (skysqlinc/skysql-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Skysql, 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.
8 Skysql tools catalogued and risk-classified — across an index of 43,000+ MCP servers.