斷開資料庫連接
AI agents use disconnect to create or update resources in MSSQL MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MSSQL MCP Server environment.
Disconnecting a database connection is a reversible state-management action. It does not destroy data, execute arbitrary code, or cause financial impact. It temporarily closes the connection but does not prevent reconnection or affect stored data. This qualifies as Write (state modification) rather than Read (which would be querying) or more severe categories.
From the tool's definition Tool name: 'disconnect' with description indicating closing/terminating a database connection. The description '斷開資料庫連接' translates to 'disconnect database connection' from Traditional Chinese.
Attacks that exploit this kind of access
斷開資料庫連接. It is categorised as a Write tool in the MSSQL MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MSSQL MCP Server MCP server in PolicyLayer and add a rule for disconnect: 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 MSSQL MCP Server. Nothing to install.
disconnect 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 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. 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 is provided by the MSSQL MCP Server MCP server (nakiriyuuzu/mssql-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 →