OSV Dependency Vulnerability Check MCP Server

Overview Schema Source Related Servers Discussions Admin

List all known vulnerabilities of a package (free)

list_package_vulnerabilities

Read-onlyIdempotent

List every OSV.dev advisory for a package across all versions, with affected ranges and fixed versions, to find security issues and pick safe dependency versions.

Instructions

WHAT: List every OSV.dev advisory recorded for one package across all of its versions (no version needed), with the affected version ranges and fixed versions for that package. WHEN TO USE: "what security issues has lodash had?", choosing a safe version before adding a dependency, or browsing advisories for a package when you have no exact version or advisory ID. WHEN NOT TO USE: to check exact pinned versions or a manifest and get upgrade recommendations use check_dependency_vulnerabilities (paid); for the full record of one advisory use get_vulnerability_details (free). BEHAVIOR: POST /v1/query to api.osv.dev without a version; follows OSV pagination up to 10 pages; typically 1-3 s. An unknown package name returns 0 rows, not an error (OSV does not distinguish). COST: free; no APIFY_TOKEN, nothing sent to Fairquery or Apify; OSV documents no rate limit. RETURNS: one type="vulnerability" summary row per advisory, newest published first; Errors: INVALID_ECOSYSTEM, OSV_FETCH_FAILED (retryable). PARAMETERS: ecosystem accepts aliases (pip -> PyPI, cargo -> crates.io, gem -> RubyGems, composer -> Packagist, golang -> Go, java -> Maven) and other OSV ecosystem names verbatim (e.g. "Debian:12"). name must match the published package exactly; affected_ranges and fixed_versions only cover entries for this exact package, not sibling packages the same advisory also lists. limit/offset page the sorted rows; every call re-queries OSV, which is free. withdrawn advisories are kept and carry a withdrawn timestamp. EXAMPLE: {"ecosystem":"npm","name":"lodash","limit":2} -> total 10, newest first: {"id":"GHSA-r5fr-rjxr-66jc","severity":"HIGH","affected_ranges":[{"introduced":"4.0.0","fixed":"4.18.0"}],"fixed_versions":["4.18.0"],...}, then GHSA-f23m-r3pf-42rh.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	Required. Package name exactly as published: npm "lodash" or "@scope/pkg", PyPI "django", Go module path "github.com/gin-gonic/gin", Maven "groupId:artifactId". Example: "lodash"
`limit`	No	Optional page size, integer 1-500, default 100. Example: 50
`offset`	No	Optional, integer >= 0, default 0; use nextOffset from the previous page. Example: 100
`ecosystem`	Yes	Required. OSV ecosystem, case-insensitive for the common ones: npm, PyPI, Go, Maven, crates.io, RubyGems, NuGet, Packagist, Pub, Hex (aliases pip/cargo/gem/composer accepted). Example: "npm"

Output Schema

TableJSON Schema

Name	Required	Description
`count`	Yes	Rows in this page
`items`	Yes	type="vulnerability" rows or one type="error" row
`total`	Yes	Advisories found for the package
`offset`	Yes
`hasMore`	Yes
`nextOffset`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.2.0Oct 18, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already cover the read-only/open-world/idempotent safety profile, but the description adds substantially more: POST /v1/query with no version body, pagination capped at 10 pages, 1-3s latency, unknown package returning 0 rows instead of an error, withdrawn advisories retained, and named error codes (INVALID_ECOSYSTEM, OSV_FETCH_FAILED). This is exactly the extra behavioral context annotations cannot express.

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

Conciseness4/5

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

Labeled sections (WHAT/WHEN TO USE/WHEN NOT TO USE/BEHAVIOR/COST/RETURNS/PARAMETERS/EXAMPLE) make it highly scannable, and the most decision-relevant content is front-loaded. It runs long, and the free/no-rate-limit point recurs across COST and PARAMETERS, which keeps it from a perfect score.

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?

With an output schema present and 100% schema coverage, the description still supplies the error taxonomy, pagination model, cost/auth posture, and a concrete worked example with a sample response. An agent has everything needed to call it correctly on the first attempt.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, and the description still adds real semantics: alias mapping plus verbatim OSV ecosystem names like 'Debian:12', exact-package-name matching, the caveat that affected_ranges/fixed_versions cover only this package and not sibling packages in the same advisory, and that offset/limit re-query OSV on every call. It falls short of 5 only because the ecosystem alias list partially duplicates the schema.

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 WHAT line states a specific verb+resource+scope: list every OSV.dev advisory for one package across all versions, no version required. It also immediately distinguishes itself from the 'exact pinned version' case covered by the sibling check tool.

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?

Explicit WHEN TO USE (sample questions, choosing a safe version, browsing with no version/advisory ID) and WHEN NOT TO USE that names both siblings with the condition that selects them (exact pinned versions/manifest -> check_dependency_vulnerabilities; full single-advisory record -> get_vulnerability_details). Nothing is left to inference.

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

Deploy Server