AI agents call check_upload_status to retrieve information from Rag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns information about an existing upload session's status and details. It has no side effects, does not modify data, execute operations, or incur costs. The verb 'Retrieve' and absence of any action-triggering capability clearly place it in the Read category with low severity.
From the tool's definition Tool name is 'check_upload_status' and description states it 'Retrieve[s] details and file status for an upload session' - purely retrieval with no modification or execution.
Attacks that exploit this kind of access
Retrieve details and file status for an upload session. It is categorised as a Read tool in the Rag MCP Server, which means it retrieves data without modifying state.
Register the Rag MCP server in PolicyLayer and add a rule for check_upload_status: 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 Rag. Nothing to install.
check_upload_status 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 check_upload_status 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 check_upload_status. 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.
check_upload_status is provided by the Rag MCP server (mrankitvish/rag-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 →