AI agents call use_connection to retrieve information from Mysql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The server explicitly restricts operations to read-only access and prevents writes, indicating this tool supports querying rather than modification. Without a description, there is some ambiguity about whether this merely selects a connection (Read) or enables actions.
From the tool's definition Server is described as 'safe, read-only access to MySQL databases' that 'preventing write operations.' Tool name 'use_connection' suggests establishing a connection to a database. However, the tool description is empty, limiting confidence in the assessment.
Attacks that exploit this kind of access
use_connection. It is categorised as a Read tool in the Mysql MCP Server, which means it retrieves data without modifying state.
Register the Mysql MCP server in PolicyLayer and add a rule for use_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. Nothing to install.
use_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 use_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 use_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.
use_connection is provided by the Mysql MCP server (rlembo06/mysql-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 →