AI agents use put_object to create or update resources in S3 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your S3 environment.
put_object creates or overwrites objects in S3, which is a reversible write operation—the data can be modified or deleted later. It is not destructive because the action itself is not permanent and can be undone.
From the tool's definition Tool name 'put_object' and description 'Puts an object into an S3 bucket' indicate creating or uploading data to S3.
Attacks that exploit this kind of access
Puts an object into an S3 bucket. It is categorised as a Write tool in the S3 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the S3 MCP server in PolicyLayer and add a rule for put_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 S3. Nothing to install.
put_object 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 put_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 put_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.
put_object is provided by the S3 MCP server (konmam/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 →