現在のデータベース接続を切断します
AI agents use disconnect_database to create or update resources in MySQL MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MySQL MCP Server environment.
Disconnecting a database is a reversible state change (the connection can be re-established via 'connect_database' or 'connect_by_profile'). It modifies the connection state but does not create, delete, or persist any data. While it could disrupt active operations, this is a normal administrative action with minimal blast radius.
From the tool's definition Tool name 'disconnect_database' and description indicate it closes an active database connection. The Japanese description translates to 'Disconnect the current database connection.'
Attacks that exploit this kind of access
現在のデータベース接続を切断します. It is categorised as a Write tool in the MySQL MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MySQL MCP Server MCP server in PolicyLayer and add a rule for disconnect_database: 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 MCP Server. Nothing to install.
disconnect_database is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the disconnect_database 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 disconnect_database. 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.
disconnect_database is provided by the MySQL MCP Server MCP server (yuki777/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 →