Set a MySQL system variable.
AI agents invoke set_variable to trigger actions in MCP MySQL Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Setting MySQL system variables modifies server runtime behavior (e.g., sql_mode, max_connections, innodb settings). This is not a simple write to user data but an execution-level operation that affects server configuration and can have broad system-wide effects. It is reversible in theory but can destabilize the server or bypass security controls, warranting high severity.
From the tool's definition Set a MySQL system variable
Attacks that exploit this kind of access
Set a MySQL system variable. It is categorised as a Execute tool in the MCP MySQL Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP MySQL Server MCP server in PolicyLayer and add a rule for set_variable: 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 Server. Nothing to install.
set_variable is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the set_variable 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 set_variable. 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.
set_variable is provided by the MCP MySQL Server MCP server (kami2k1/mcp-mysql). 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 →