Execute a query within an active transaction
AI agents invoke execute_in_transaction to trigger actions in DBeaver 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 queries within a transaction context, making it an Execute category tool. While the transaction wrapper could theoretically limit scope, the tool itself does not restrict query type—it could execute SELECT, INSERT, UPDATE, DELETE, or DDL statements depending on the query argument.
From the tool's definition Tool name 'execute_in_transaction' and description 'Execute a query within an active transaction' indicate the ability to run arbitrary queries.
Documented attack patterns abuse exactly the kind of access execute_in_transaction gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DBeaver MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_in_transaction:
{
"version": "1",
"default": "deny",
"tools": {
"execute_in_transaction": {
"limits": [
{
"counter": "execute_in_transaction_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_in_transaction 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 a query within an active transaction. It is categorised as a Execute tool in the DBeaver MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the DBeaver MCP Server MCP server in PolicyLayer and add a rule for execute_in_transaction: 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 DBeaver MCP Server. Nothing to install.
execute_in_transaction 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_in_transaction 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_in_transaction. 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_in_transaction is provided by the DBeaver MCP Server MCP server (srthkdev/omnisql-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 DBeaver MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 DBeaver MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.