AI agents call resolve_dependencies to retrieve information from PyPI Query MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The server is described as a query server for PyPI package information and dependency analysis. All sibling tools are read-only operations (get, check, download statistics). 'resolve_dependencies' most likely queries and resolves a dependency graph from PyPI without modifying any state. The description is empty, which lowers confidence, but context strongly implies a read operation.
From the tool's definition Tool name 'resolve_dependencies' on a PyPI query server alongside sibling tools like 'get_package_dependencies', 'get_package_info', and 'check_package_python_compatibility' — all of which are read/query operations against PyPI.
Documented attack patterns abuse exactly the kind of access resolve_dependencies 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 resolve_dependencies:
{
"version": "1",
"default": "deny",
"tools": {
"resolve_dependencies": {}
}
}resolve_dependencies 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.
resolve_dependencies. It is categorised as a Read tool in the PyPI Query MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PyPI Query MCP Server MCP server in PolicyLayer and add a rule for resolve_dependencies: 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.
resolve_dependencies 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 resolve_dependencies 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 resolve_dependencies. 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.
resolve_dependencies 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.