Connect to MySQL database using URL or config
AI agents invoke connect_db 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.
Connecting to a database is an external operation that initiates a session with a remote system. It is not purely a read (no data is retrieved) nor a write (no data is modified), but it executes an external action — establishing a live connection — whose effects (session state, credential exposure, network activity) depend on the arguments provided.
From the tool's definition 'Connect to MySQL database using URL or config' — establishes an active database connection using provided credentials/configuration
Attacks that exploit this kind of access
Connect to MySQL database using URL or config. 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 connect_db: 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.
connect_db 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 connect_db 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 connect_db. 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.
connect_db is provided by the MCP MySQL Server MCP server (kevinbin/mcp-mysql-server). 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 →