Read an object
AI agents call s3_object_read to retrieve information from AWS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from S3 without side effects. Reading objects is a safe, non-destructive operation. The low severity reflects minimal blast radius—an AI agent cannot cause data loss, financial harm, or trigger external operations through object reads alone. Confidence is high due to explicit 'read' semantics in both name and description.
From the tool's definition Tool name 's3_object_read' and description 'Read an object' directly indicate a retrieval operation with no modification or deletion.
Attacks that exploit this kind of access
Read an object. It is categorised as a Read tool in the AWS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AWS MCP Server MCP server in PolicyLayer and add a rule for s3_object_read: 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 AWS MCP Server. Nothing to install.
s3_object_read 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 s3_object_read 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 s3_object_read. 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.
s3_object_read is provided by the AWS MCP Server MCP server (rishikavikondala/mcp-server-aws). 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 →