NPMScan

Search npm packages

search_packages

Read-only

Search the npm registry by name or keywords. Each result includes its current weekly/monthly download counts, dependentsCount (how many other npm packages depend on it), topPackagesRank (position among npmscan's own top-100k-by-downloads snapshot — not live, but a second independent popularity signal), and deterministic (not model-generated) popularityTier/maintenanceTier labels — a package matching the query with a 'very-low' popularityTier, zero dependents, or a 'stale' maintenanceTier is very likely an abandoned, copy-paste, or squatted package, not a real contender, regardless of how relevant its name/description look. A result may also carry possibleTyposquatOf — set when its name is one typo away (e.g. 'raect' vs 'react') from a top-5,000 package while itself having very low popularity; treat that as a red flag to call out explicitly, not silently filter. Use these (not name recognition or the package's own README) to judge which candidates are actually established, and call get_package on your shortlist for install-script risk, TypeScript support, and GitHub stars before recommending one. Includes a link to each package's full npmscan.com risk/analysis page.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Max results to return (default 20, max 50)
`query`	Yes	Search text, e.g. a package name or keywords

Output Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes
`total`	Yes
`results`	Yes

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses important behavioral nuances beyond the annotations: topPackagesRank is not live, labels are deterministic rather than model-generated, low-popularity/stale results are likely abandoned or squatted, and possibleTyposquatOf should be called out rather than silently filtered. This gives the agent critical interpretation guidance that readOnlyHint/openWorldHint do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but high-density: every sentence adds interpretive or routing value. It front-loads the core search action and then layers result-signal meaning, warning signs, and follow-up recommendations in a logical order. No sentences are filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a search tool feeding into a security-analysis workflow, the description covers result interpretation, caveats, red flags, and the recommended next step (get_package). The output schema handles structural return details, so the description does not need to restate them. An agent has enough context to use the tool correctly and act on its output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already documents query and limit, including defaults and constraints. The description only restates the query semantics ('by name or keywords') and adds no meaningful parameter-level detail beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action and resource: searching the npm registry by name or keywords. It goes beyond a tautology by explaining what each result contains and how the tool differs from follow-up tools like get_package. An agent can immediately understand this is the entry-point search tool among the sibling set.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit guidance on when to use the results: use the popularity and maintenance signals rather than name recognition or READMEs, treat possibleTyposquatOf as a red flag, and call get_package on the shortlist for deeper vetting. This actively routes the agent to the correct next tool and prevents misuse.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All NPMScan tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0

Disambiguation4/5

Each tool targets a distinct workflow—install script analysis, transitive dependency resolution, batch OSV queries, provenance verification, CVE lookup, advisory browsing, package metadata, exact-version checks, single-package vuln checks, and search. The only mild overlap is that several get_/query_ tools return vulnerability data, but the descriptions clearly delineate when to use each.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern: get_package, query_vulnerabilities, analyze_transitive_dependencies, check_package_provenance, etc. There are no mixed casing styles or vague verbs, making the set highly predictable.

Tool Count5/5

10 tools is well-scoped for an npm security scanning server. Each tool earns its place by covering a distinct facet of the domain without redundancy or bloat.

Completeness4/5

The surface covers package discovery, metadata, exact-version vulnerability checks, batch scanning, transitive graph analysis, install-script heuristics, provenance, advisories, and CVE enrichment. Minor gaps remain—e.g. no full tarball code review and maintainer-history red flags are explicitly out of scope—but core agent workflows are covered.

Resources

Need Help?