AI agents call get_table_schema to retrieve information from Mysql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves schema metadata (column definitions, types, constraints) from a MySQL table without modifying any data or executing code. It is a pure read operation with no side effects, making it a Read category tool. Severity is low because schema information is typically non-sensitive compared to actual data, and there is no destructive or execution capability.
From the tool's definition Tool description states 'Get schema information for a specific table' and server description emphasizes 'read-only access to MySQL database schema', with purpose for 'safe backend development'.
Attacks that exploit this kind of access
Get schema information for a specific table. It is categorised as a Read tool in the Mysql MCP Server, which means it retrieves data without modifying state.
Register the Mysql MCP server in PolicyLayer and add a rule for get_table_schema: 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 Mysql. Nothing to install.
get_table_schema 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_table_schema 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_table_schema. 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_table_schema is provided by the Mysql MCP server (yukihito-jokyu/mysql-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 →