Generate a pre-signed URL for accessing an object.
AI agents call get_object to retrieve information from AWS S3 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The get_object tool retrieves or generates access to data without side effects. While the sibling tools include write and destructive operations (put_object, delete_object), this specific tool only provides read access via pre-signed URLs.
From the tool's definition Tool description states 'Generate a pre-signed URL for accessing an object.' The action is generating access to retrieve data, with no modification, deletion, or code execution. This is a read operation.
Attacks that exploit this kind of access
Generate a pre-signed URL for accessing an object. It is categorised as a Read tool in the AWS S3 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AWS S3 MCP Server MCP server in PolicyLayer and add a rule for get_object: 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 S3 MCP Server. Nothing to install.
get_object 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 get_object 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 get_object. 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.
get_object is provided by the AWS S3 MCP Server MCP server (openworkspace-o1/aws-ow-s3-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 →