关闭数据库连接。我会在完成操作后调用此工具释放资源。如果有活动事务会自动回滚。
AI agents use db_close to create or update resources in MCP Toolkit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Toolkit environment.
db_close closes a database connection and automatically rolls back any active transactions. While primarily a cleanup/resource management operation, the automatic rollback of uncommitted transactions constitutes a modification of database state that could lose data if called prematurely or unexpectedly. This makes it Write rather than Read.
From the tool's definition Tool description states '关闭数据库连接。我会在完成操作后调用此工具释放资源。如果有活动事务会自动回滚。' (Close database connection. I will call this tool to release resources after completing operations. If there are active transactions, they will be automatically rolled back.)
Attacks that exploit this kind of access
关闭数据库连接。我会在完成操作后调用此工具释放资源。如果有活动事务会自动回滚。. It is categorised as a Write tool in the MCP Toolkit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Toolkit MCP server in PolicyLayer and add a rule for db_close: 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 Toolkit. Nothing to install.
db_close 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 db_close 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 db_close. 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.
db_close is provided by the MCP Toolkit MCP server (zxfgds/mcp-toolkit). 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 →