x402-gated safety checker for npm and PyPI packages. Built for AI coding agents to call before running npm install or pip install — flags nonexistent/typosquatted names, known CVEs (OSV.dev), and suspiciously new or low-download packages. $0.005 USDC per check on Base mainnet
Scored across 1 tool
With only one tool, there is no possibility of overlapping purposes or confusion between tools. The single tool's purpose is clearly defined.
The single tool follows a clear verb_noun pattern (check_package_safety). With only one tool, naming consistency is inherently maintained.
One tool is borderline for a useful server; it feels thin, but the narrow purpose of checking package safety may justify a minimal surface. Still, more related operations could reasonably be expected.
The tool covers the core stated purpose of checking package safety for npm and PyPI. Minor gaps exist, such as version-specific checks, detailed vulnerability reporting, or batch checking, but agents can work around them.
Check whether an npm or PyPI package is safe to install. Costs $0.005 USDC via x402 per call.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Exact package name to check for safety before installing | |
| ecosystem | Yes | Package ecosystem to check |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for behavioral disclosure. It mentions the cost mechanism, which is valuable, but does not disclose what happens when a package is unsafe (e.g., return type, possible errors) or any side effects. The core behavior is stated, but depth is lacking.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with 18 words, highly concise. It front-loads the core purpose and adds the cost detail efficiently. However, it could benefit from slight restructuring for clarity (e.g., separating cost info).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 parameters, no output schema, no siblings), the description covers the essential purpose and cost but fails to describe the return value or possible outputs. With no output schema, the agent would benefit from knowing the response format. The description is functionally complete for a basic check but leaves an important gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%: both 'name' and 'ecosystem' have descriptions. The tool description only adds cost context, not parameter details, so it does not meaningfully augment the schema. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description states exactly what the tool does: 'Check whether an npm or PyPI package is safe to install.' The verb 'check' and resource 'package safety' are specific, and the ecosystems npm and PyPI are clearly mentioned. No siblings exist, so differentiation is not needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives or when not to use it. It only mentions a cost of $0.005 USDC via x402 per call, which is a constraint but not usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_package_safety
Add one secure layer between your agents and this server.