AI agents invoke execute_sql_query to trigger actions in MCP Databricks 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 runs SQL queries against a live data warehouse with effects that depend on the query content. While the sibling tools (describe_*) are Read-only, execute_sql_query can run any SQL statement including SELECT, INSERT, UPDATE, DELETE, or DROP commands. Without explicit restrictions in the tool description, it must be classified as Execute (with potential for Destructive misuse).
From the tool's definition Tool name 'execute_sql_query' combined with server description stating it 'enables AI assistants to directly query Databricks data warehouses' and 'executing SQL queries against Databricks using the Statement Execution API'.
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 MCP Databricks 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.
execute_sql_query. It is categorised as a Execute tool in the MCP Databricks Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Databricks 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 MCP Databricks 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 MCP Databricks Server MCP server (rafaelcartenet/mcp-databricks-server). 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 Databricks Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 MCP Databricks Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.