AI agents call get_database_info to retrieve information from MCP MySQL Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about databases without modifying, executing code, destroying data, or affecting financial systems. It is a query/inspection operation. The low severity reflects that database schema/metadata leakage has limited immediate impact compared to data modification or code execution, though it could inform subsequent attacks.
From the tool's definition Tool name 'get_database_info' and description 'Get database information' indicate a retrieval operation with no side effects. The verb 'Get' and the informational nature of the request (querying metadata about databases) are characteristic of Read operations.
Documented attack patterns abuse exactly the kind of access get_database_info gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP MySQL Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_database_info:
{
"version": "1",
"default": "deny",
"tools": {
"get_database_info": {}
}
}get_database_info is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get database information. It is categorised as a Read tool in the MCP MySQL Server MCP Server, which means it retrieves data without modifying state.
Register the MCP MySQL Server MCP server in PolicyLayer and add a rule for get_database_info: 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 MySQL Server. Nothing to install.
get_database_info 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_info 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_info. 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_info is provided by the MCP MySQL Server MCP server (liliangshan/mcp-server-mysql). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP MySQL Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 MCP MySQL Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.