AI agents call set_members to retrieve information from Amazon Redshift MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The description explicitly states this is a GET operation to retrieve members of a set, indicating a read-only query with no modifications. Severity is low as it only retrieves membership data. Confidence is slightly reduced because the tool name 'set_members' could imply a write/update operation, but the description clarifies it is a read.
From the tool's definition 'Get all members in set' — retrieves/queries data with no indicated side effects
Documented attack patterns abuse exactly the kind of access set_members gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Amazon Redshift MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for set_members:
{
"version": "1",
"default": "deny",
"tools": {
"set_members": {}
}
} set_members is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get all members in set. It is categorised as a Read tool in the Amazon Redshift MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Amazon Redshift MCP Server MCP server in PolicyLayer and add a rule for set_members: 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 Amazon Redshift MCP Server. Nothing to install.
set_members 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 set_members 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_members. 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_members is provided by the Amazon Redshift MCP Server MCP server (awslabs.redshift-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Amazon Redshift MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
805 Amazon Redshift MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.