Get the latest version of a Python package from PyPI.
AI agents call get_python_package to retrieve information from Versionator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries PyPI to fetch version and metadata information about Python packages. It retrieves data without side effects—no code execution, no data modification, and no destructive actions. The broader server description confirms it 'queries' registries to 'retrieve' version and metadata, consistent with Read category.
From the tool's definition Tool name 'get_python_package' and description 'Get the latest version of a Python package from PyPI' indicate a query operation that retrieves package metadata without modifying or executing any code.
Attacks that exploit this kind of access
Get the latest version of a Python package from PyPI. It is categorised as a Read tool in the Versionator MCP Server, which means it retrieves data without modifying state.
Register the Versionator MCP server in PolicyLayer and add a rule for get_python_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 Versionator. Nothing to install.
get_python_package 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_python_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 get_python_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.
get_python_package is provided by the Versionator MCP server (trianglegrrl/versionator-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 →