Upload an object to S3
AI agents use s3_object_upload to create or update resources in AWS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AWS MCP Server environment.
Upload operations create or modify data but are generally reversible through deletion or re-uploading. The severity is high because an agent could upload malicious files, trojans, or large-scale data to a production S3 bucket, potentially affecting downstream applications that consume those objects, or incurring unexpected costs.
From the tool's definition The tool 'uploads an object to S3,' which creates or modifies data in a reversible manner. This is a write operation that creates new objects or overwrites existing ones in cloud storage.
Attacks that exploit this kind of access
Upload an object to S3. It is categorised as a Write tool in the AWS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AWS MCP Server MCP server in PolicyLayer and add a rule for s3_object_upload: 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_upload is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the s3_object_upload 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_upload. 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_upload 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 →