查询指定表的详细结构，包含字段注释、索引、外键等信息
AI agents call describe_table to retrieve information from Keevor Mysql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries table structure metadata only. It performs a read-only operation with no side effects—no data is created, modified, deleted, or executed. Even though a sibling tool 'execute_sql' could be destructive, this specific tool is limited to schema inspection, making it a Read category with low severity risk.
From the tool's definition Tool name 'describe_table' and description '查询指定表的详细结构，包含字段注释、索引、外键等信息' (query specified table's detailed structure, including field comments, indexes, foreign keys, etc.) indicate retrieval of schema metadata without modification.
Attacks that exploit this kind of access
查询指定表的详细结构，包含字段注释、索引、外键等信息. It is categorised as a Read tool in the Keevor Mysql MCP Server, which means it retrieves data without modifying state.
Register the Keevor Mysql MCP server in PolicyLayer and add a rule for describe_table: 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 Keevor Mysql. Nothing to install.
describe_table 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 describe_table 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 describe_table. 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.
describe_table is provided by the Keevor Mysql MCP server (keevor/keevor-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 →