Check mysql connection
AI agents call sql_check_connection to retrieve information from MCP MySQL App without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only connection test. It does not execute queries, modify data, delete records, or trigger external operations. While it is part of a MCP MySQL server that includes sql_query (which could be Execute/Destructive depending on arguments), this specific tool only checks connection status, which is a benign diagnostic operation with minimal blast radius if misused.
From the tool's definition Tool name is 'sql_check_connection' and description states it will 'Check mysql connection'. This is a diagnostic operation that tests connectivity without retrieving, modifying, or executing arbitrary operations against the database.
Attacks that exploit this kind of access
Check mysql connection. It is categorised as a Read tool in the MCP MySQL App MCP Server, which means it retrieves data without modifying state.
Register the MCP MySQL App MCP server in PolicyLayer and add a rule for sql_check_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 MCP MySQL App. Nothing to install.
sql_check_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 sql_check_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 sql_check_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.
sql_check_connection is provided by the MCP MySQL App MCP server (zalab-inc/mcp-mysql-app). 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 →