Get package info and download stats from npm or PyPI.
AI agents call check_package to retrieve information from Github Insight without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries package metadata and statistics from public package registries. It has no capability to modify packages, execute code, delete data, or commit financial transactions. The operation is purely informational with no side effects. The blast radius of misuse is minimal—an AI agent could only retrieve publicly available package information.
From the tool's definition Tool retrieves package info and download stats from npm or PyPI. Verbs indicate read operations: 'Get' with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Get package info and download stats from npm or PyPI. It is categorised as a Read tool in the Github Insight MCP Server, which means it retrieves data without modifying state.
Register the Github Insight MCP server in PolicyLayer and add a rule for check_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 Github Insight. Nothing to install.
check_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 check_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 check_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.
check_package is provided by the Github Insight MCP server (wjddusrb03/github-insight-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 →