Test a named database connection
AI agents call test-connection to retrieve information from Mysql Multi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Testing a connection is a read-only operation that merely validates that a database connection is functional. It has no side effects, does not retrieve application data, does not execute arbitrary SQL, and does not modify any state.
From the tool's definition Tool name 'test-connection' and description 'Test a named database connection' indicate a diagnostic operation that verifies connectivity without modifying data or executing arbitrary queries.
Attacks that exploit this kind of access
Test a named database connection. It is categorised as a Read tool in the Mysql Multi MCP Server, which means it retrieves data without modifying state.
Register the Mysql Multi MCP server in PolicyLayer and add a rule for test-connection: 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 Mysql Multi. Nothing to install.
test-connection is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the test-connection 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 test-connection. 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.
test-connection is provided by the Mysql Multi MCP server (pchimbolo/mysql-multi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
test-connection is one line of Mysql Multi's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →