Execute any SQL statement against the PostgreSQL database, including INSERT, UPDATE, DELETE, and DDL operations. This tool is restricted to specific GitHub users and can perform write transactions. USE WITH CAUTION - this can modify or delete data.
AI agents invoke executeDatabase to trigger actions in My Credentials MCP 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.
While the tool description mentions INSERT, UPDATE, DELETE, and DDL operations (which span Write and Destructive categories), the primary capability is unrestricted SQL execution. The tool allows arbitrary SQL statements, making it fundamentally an Execute tool whose effects depend entirely on the SQL arguments provided.
From the tool's definition 'Execute any SQL statement against the PostgreSQL database, including INSERT, UPDATE, DELETE, and DDL operations' and 'this tool is restricted to specific GitHub users and can perform write transactions' and 'USE WITH CAUTION - this can modify or delete data'
Attacks that exploit this kind of access
Execute any SQL statement against the PostgreSQL database, including INSERT, UPDATE, DELETE, and DDL operations. This tool is restricted to specific GitHub users and can perform write transactions. USE WITH CAUTION - this can modify or delete data. It is categorised as a Execute tool in the My Credentials MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the My Credentials MCP Server MCP server in PolicyLayer and add a rule for executeDatabase: 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 My Credentials MCP Server. Nothing to install.
executeDatabase 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 executeDatabase 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 executeDatabase. 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.
executeDatabase is provided by the My Credentials MCP Server MCP server (preangelleo/my-credentials-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 →