AI agents use switch-database to create or update resources in Sql — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sql environment.
This tool performs a state-changing operation that affects which database is the active target for subsequent operations. It's reversible (can switch back), so it doesn't qualify as Destructive. It doesn't directly read data (Read category), nor does it execute arbitrary code or queries (Execute category).
From the tool's definition Tool description: 'Switch to a different database on the connected server.' This action modifies the connection state and context, changing which database subsequent queries operate against.
Attacks that exploit this kind of access
Switch to a different database on the connected server. Note: PostgreSQL requires reconnection. It is categorised as a Write tool in the Sql MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sql MCP server in PolicyLayer and add a rule for switch-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 Sql. Nothing to install.
switch-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 switch-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 switch-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.
switch-database is provided by the Sql MCP server (nakiriyuuzu/sql-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 →