AI agents use close_database to create or update resources in Re — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Re environment.
Despite the empty description, the semantics of 'close_database' indicate a Write-category operation: it modifies the state of an open resource connection reversibly. It does not retrieve data (Read), delete data (Destructive), move money (Financial), or execute arbitrary code (Execute).
From the tool's definition Tool name 'close_database' suggests closing/releasing a database connection or resource. While the description is empty, the action of closing a database is a reversible state change (the database remains intact; only the connection is terminated).
Attacks that exploit this kind of access
close_database. It is categorised as a Write tool in the Re MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Re MCP server in PolicyLayer and add a rule for close_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 Re. Nothing to install.
close_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 close_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 close_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.
close_database is provided by the Re MCP server (jtsylve/re-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 →