AI agents call get_object_bytes to retrieve information from Rustfs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves object data from S3-compatible storage without side effects. It is purely a Read operation. Severity is medium rather than low because: (1) it could expose sensitive data stored in S3 if an agent misuses it against unintended buckets/objects, and (2) the ~10MiB cap and base64 encoding suggest it handles potentially large or sensitive payloads.
From the tool's definition Tool description states 'Download an object as base64 bytes', which retrieves data from S3 without modification. The name 'get_object_bytes' confirms read-only retrieval semantics.
Attacks that exploit this kind of access
Download an object as base64 bytes (browser download; ~10MiB cap). It is categorised as a Read tool in the Rustfs MCP Server, which means it retrieves data without modifying state.
Register the Rustfs MCP server in PolicyLayer and add a rule for get_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.
get_object_bytes 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_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 get_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.
get_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 →