List all configured database connections (passwords hidden)
AI agents call list-connections to retrieve information from Mysql Multi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays metadata about existing database connections without modifying, deleting, or executing anything. The fact that passwords are hidden further confirms it is a safe read-only operation. No blast radius from misuse—an AI agent running this tool can only enumerate connections already configured by the user.
From the tool's definition Tool name is 'list-connections' and description states it 'List all configured database connections (passwords hidden)'. This is a pure query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List all configured database connections (passwords hidden). It is categorised as a Read tool in the Mysql Multi MCP Server, which means it retrieves data without modifying state.
Register the Mysql Multi MCP server in PolicyLayer and add a rule for list-connections: 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 Multi. Nothing to install.
list-connections 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 list-connections 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 list-connections. 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.
list-connections is provided by the Mysql Multi MCP server (pchimbolo/mysql-multi-mcp). 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 →