AI agents call get-database-schema-tool to retrieve information from Sql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns database schema metadata (tables, columns, types, etc.) without side effects. It is a passive information retrieval operation consistent with the Read category. The server context confirms it provides 'SELECT queries' and 'get schema' capabilities. Severity is low because schema information is typically non-sensitive metadata, and retrieval causes no system changes.
From the tool's definition Tool name contains 'get' and description states 'Retrieves schema information' — purely read-only operation with no data modification or deletion.
Attacks that exploit this kind of access
Retrieves schema information for specified databases. It is categorised as a Read tool in the Sql MCP Server, which means it retrieves data without modifying state.
Register the Sql MCP server in PolicyLayer and add a rule for get-database-schema-tool: 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 Sql. Nothing to install.
get-database-schema-tool 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-database-schema-tool 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-database-schema-tool. 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-database-schema-tool is provided by the Sql MCP server (prahveent/sql-mcp-server). 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 →