AI agents invoke download_package to trigger actions in PyPI Query MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The name 'download_package' strongly suggests it fetches and saves a package to the local filesystem, which is an external operation with side effects beyond a simple read. However, the description is empty, reducing confidence. It could also merely retrieve metadata or a URL (Read), but 'download' implies writing data to disk or executing a retrieval operation.
From the tool's definition Tool name 'download_package' on a PyPI server; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access download_package gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PyPI Query MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for download_package:
{
"version": "1",
"default": "deny",
"tools": {
"download_package": {
"limits": [
{
"counter": "download_package_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}download_package stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
download_package. It is categorised as a Execute tool in the PyPI Query MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PyPI Query MCP Server MCP server in PolicyLayer and add a rule for download_package: 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 PyPI Query MCP Server. Nothing to install.
download_package is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the download_package 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 download_package. 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.
download_package is provided by the PyPI Query MCP Server MCP server (loonghao/pypi-query-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PyPI Query MCP Server, 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.
10 PyPI Query MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.