AI agents invoke execute_dbsql to trigger actions in Databricks 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.
SQL execution tools are Execute-category because they run code whose effects depend entirely on the SQL arguments provided—a malicious agent could execute arbitrary queries including data exfiltration, modification, or (if the Databricks user has permissions) destructive operations.
From the tool's definition Tool name 'execute_dbsql' indicates SQL execution capability. Server description confirms 'SQL execution' is supported via Databricks SDK. Sibling tools include 'cancel_query' and 'cancel_statement', reinforcing that this server executes queries.
Documented attack patterns abuse exactly the kind of access execute_dbsql gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Databricks MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_dbsql:
{
"version": "1",
"default": "deny",
"tools": {
"execute_dbsql": {
"limits": [
{
"counter": "execute_dbsql_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_dbsql 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_dbsql. It is categorised as a Execute tool in the Databricks MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Databricks MCP Server MCP server in PolicyLayer and add a rule for execute_dbsql: 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 Databricks MCP Server. Nothing to install.
execute_dbsql 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_dbsql 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_dbsql. 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_dbsql is provided by the Databricks MCP Server MCP server (pulkitxchadha/awesome-databricks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Databricks 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.
86 Databricks MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.