AI agents invoke reconnect_database to trigger actions in Qtz Iris. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external operation — re-establishing a database connection — which has side effects beyond simple data retrieval. It does not read, write, or delete data, but it executes a connection lifecycle operation that could affect ongoing sessions and access states. Misuse could disrupt active queries or reset transaction contexts.
From the tool's definition 重新连接到 IRIS 数据库。当数据库连接断开或需要刷新连接时使用此工具。 (Reconnect to IRIS database; use when connection is lost or needs refreshing)
Attacks that exploit this kind of access
重新连接到 IRIS 数据库。当数据库连接断开或需要刷新连接时使用此工具。. It is categorised as a Execute tool in the Qtz Iris MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Qtz Iris MCP server in PolicyLayer and add a rule for reconnect_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 Qtz Iris. Nothing to install.
reconnect_database is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the reconnect_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 reconnect_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.
reconnect_database is provided by the Qtz Iris MCP server (qtz-iris-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 →