AI agents call translate-sql to retrieve information from Sql2odata without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool translates SQL statements into OData v4 query syntax. It does not execute any SQL against a database, nor does it modify any data. It is purely a translation/conversion utility that takes SQL text as input and returns OData query syntax as output.
From the tool's definition 'Translate a SQL statement into OData v4 query syntax' - the tool performs translation/conversion of SQL to OData syntax
Attacks that exploit this kind of access
Translate a SQL statement into OData v4 query syntax. Supports SELECT, INSERT, UPDATE, DELETE with WHERE, JOIN, GROUP BY, LIKE, IN, BETWEEN, IS NULL, LIMIT, OFFSET and more. It is categorised as a Read tool in the Sql2odata MCP Server, which means it retrieves data without modifying state.
Register the Sql2odata MCP server in PolicyLayer and add a rule for translate-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 Sql2odata. Nothing to install.
translate-sql is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the translate-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 translate-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.
translate-sql 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 →