get_schema_details
AI agents call get_schema_details to retrieve information from Mcp Ohmy Sql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves structural metadata about a database schema (tables, columns, constraints, etc.) without modifying or executing arbitrary operations. It is informational and read-only by nature. Even if it returned sensitive schema details, the blast radius is limited to information disclosure rather than data modification or deletion.
From the tool's definition Tool name 'get_schema_details' indicates retrieval of database schema information. The description is empty, but sibling tools on this server include 'execute_select_statement', 'list_databases', and 'list_tables', which are all Read operations.
Attacks that exploit this kind of access
get_schema_details. It is categorised as a Read tool in the Mcp Ohmy Sql MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ohmy Sql MCP server in PolicyLayer and add a rule for get_schema_details: 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 Ohmy Sql. Nothing to install.
get_schema_details 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 get_schema_details 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 get_schema_details. 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.
get_schema_details is provided by the Mcp Ohmy Sql MCP server (machu-gwu/mcp_ohmy_sql-project). 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 →