AI agents use shelby_upload to create or update resources in Shelby — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Shelby environment.
The shelby_upload tool creates and writes data to decentralized storage (Aptos), which is a reversible operation. It does not execute code, delete data, or move funds, so it falls under Write category.
From the tool's definition Tool description states 'Upload a file to Shelby decentralized storage' with parameters for file content, destination blob name, and expiration. This creates new data on decentralized storage.
Attacks that exploit this kind of access
Upload a file to Shelby decentralized storage. Provide file content as text, a destination blob name, and expiration. It is categorised as a Write tool in the Shelby MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Shelby MCP server in PolicyLayer and add a rule for shelby_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 Shelby. Nothing to install.
shelby_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 shelby_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 shelby_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.
shelby_upload is provided by the Shelby MCP server (jasekeee/shelby-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 →