AI agents invoke translate-batch to trigger actions in Sql2odata. 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.
The tool translates SQL including INSERT, UPDATE, and DELETE into OData v4 requests. While it may only perform translation (Read), the server description indicates it 'enables users to convert complex SQL queries into OData-compliant requests' which implies execution of those requests.
From the tool's definition Translate multiple SQL statements into OData v4 at once. Supporting SELECT, INSERT, UPDATE, and DELETE operations.
Attacks that exploit this kind of access
Translate multiple SQL statements into OData v4 at once. Returns all results in a single response. It is categorised as a Execute tool in the Sql2odata MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sql2odata MCP server in PolicyLayer and add a rule for translate-batch: 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 Sql2odata. Nothing to install.
translate-batch 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 translate-batch 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 translate-batch. 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.
translate-batch is provided by the Sql2odata MCP server (moonraker46/sql2odata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →