AI agents use put_object_bytes to create or update resources in Rustfs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rustfs environment.
This tool creates or modifies objects in S3-compatible storage, which is reversible via delete_object or overwrite. It does not execute code, delete data irreversibly, or move funds. The 'high' severity reflects the potential blast radius: an AI agent could upload malicious files, overwrite critical objects, or fill storage with unwanted content.
From the tool's definition Tool name 'put_object_bytes' and description 'Upload an object from base64 bytes' indicate creation/modification of S3 objects. The ~10MiB cap and browser file upload context confirm write operations without deletion or code execution.
Attacks that exploit this kind of access
Upload an object from base64 bytes (browser file upload; ~10MiB cap). Empty. It is categorised as a Write tool in the Rustfs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rustfs MCP server in PolicyLayer and add a rule for put_object_bytes: 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 Rustfs. Nothing to install.
put_object_bytes 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_bytes 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_bytes. 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_bytes is provided by the Rustfs MCP server (stackblaze/rustfs-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 →