Find tables by matching table or column names in the current or specified database.
AI agents call find_tables to retrieve information from MCP Server MySQL without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
find_tables is a read-only discovery tool that retrieves metadata about existing tables and columns. It has no side effects, does not execute arbitrary code, and does not modify or delete any data. The lack of parameters in the tool name and the explicit 'find/match' semantics indicate a passive lookup operation. Severity is low because misuse cannot corrupt data or cause destructive harm.
From the tool's definition Tool description states 'Find tables by matching table or column names' — a query/search operation with no modification, creation, or deletion of data or schema.
Attacks that exploit this kind of access
Find tables by matching table or column names in the current or specified database. It is categorised as a Read tool in the MCP Server MySQL MCP Server, which means it retrieves data without modifying state.
Register the MCP Server MySQL MCP server in PolicyLayer and add a rule for find_tables: 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 Server MySQL. Nothing to install.
find_tables 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 find_tables 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 find_tables. 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.
find_tables is provided by the MCP Server MySQL MCP server (nilsir/mcp-server-mysql). 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 →