Execute a SQL query on Redshift and return results as JSON.
AI agents invoke redshift_query to trigger actions in Redshift 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.
This tool executes arbitrary SQL queries on a Redshift database. While framed as a query tool, 'Execute a SQL query' without restriction means it could run SELECT, INSERT, UPDATE, DELETE, DROP, or any other SQL statement. An AI agent could misuse it to exfiltrate data, modify records, or destroy tables.
From the tool's definition "Execute a SQL query on Redshift" — runs arbitrary SQL against a Redshift database and returns results
Attacks that exploit this kind of access
Execute a SQL query on Redshift and return results as JSON. It is categorised as a Execute tool in the Redshift MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Redshift MCP Server MCP server in PolicyLayer and add a rule for redshift_query: 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 Redshift MCP Server. Nothing to install.
redshift_query 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 redshift_query 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 redshift_query. 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.
redshift_query is provided by the Redshift MCP Server MCP server (santosh07401/redshift-mcp-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 →