AI agents call shelby_download to retrieve information from Shelby without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The shelby_download tool retrieves and returns existing data from decentralized storage without creating, modifying, deleting, or executing anything. This is a pure read operation. Severity is low because downloading file content poses minimal risk even if misused by an AI agent—the worst outcome is unauthorized access to data the agent shouldn't see, but no data is harmed or changed.
From the tool's definition Tool description states 'Download a blob from Shelby storage and return its content as text' — a retrieval operation with no modification of data.
Attacks that exploit this kind of access
Download a blob from Shelby storage and return its content as text. It is categorised as a Read tool in the Shelby MCP Server, which means it retrieves data without modifying state.
Register the Shelby MCP server in PolicyLayer and add a rule for shelby_download: 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_download 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 shelby_download 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_download. 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_download 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 →