Returns a ready-to-run curl command that uploads a genome file directly to the OpenPGx server. Execute this command in your code execution sandbox or tell the user to run it in their terminal. The command sends the file WITHOUT reading it into context. After running it, use load_profile with the ...
AI agents call get_upload_command to retrieve information from Openpgx without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool itself only returns/generates a curl command string — it does not execute it or perform the upload itself. It is a Read/query operation that produces a command string for the user or sandbox to run. However, the intent is to facilitate a genome file upload, and the description instructs execution of that command, which introduces some ambiguity.
From the tool's definition Returns a ready-to-run curl command that uploads a genome file directly to the OpenPGx server
Documented attack patterns abuse exactly the kind of access get_upload_command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Openpgx, and nothing reaches the server without passing your rules. This is the rule we recommend for get_upload_command:
{
"version": "1",
"default": "deny",
"tools": {
"get_upload_command": {}
}
}get_upload_command is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Returns a ready-to-run curl command that uploads a genome file directly to the OpenPGx server. Execute this command in your code execution sandbox or tell the user to run it in their terminal. The command sends the file WITHOUT reading it into context. After running it, use load_profile with the returned code. It is categorised as a Read tool in the Openpgx MCP Server, which means it retrieves data without modifying state.
Register the Openpgx MCP server in PolicyLayer and add a rule for get_upload_command: 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 Openpgx. Nothing to install.
get_upload_command 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_upload_command 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_upload_command. 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_upload_command is provided by the Openpgx MCP server (open-pgx/openpgx). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Openpgx, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
15 Openpgx tools catalogued and risk-classified — across an index of 43,000+ MCP servers.