Remove a named database connection from the config
AI agents call remove-connection to permanently remove resources in Mysql Multi — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a named connection from the persistent configuration is an irreversible destructive action — the connection entry is deleted from stored config. If an AI agent misuses this, all queries and operations relying on that named connection would fail, and recovery would require manually re-adding credentials/configuration.
From the tool's definition Remove a named database connection from the config
Attacks that exploit this kind of access
Remove a named database connection from the config. It is categorised as a Destructive tool in the Mysql Multi MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mysql Multi MCP server in PolicyLayer and add a rule for remove-connection: 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.
remove-connection is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove-connection 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 remove-connection. 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.
remove-connection 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 →