Skip to main content
Glama
cliwant

mcp-sam-gov

cve_lookup

Read-only

Look up NVD CVE records by ID, keyword, CPE, severity, or date range, and get each vulnerability's CISA KEV status.

Instructions

Look up NIST NVD CVE records (keyless; services.nvd.nist.gov CVE API 2.0) — exact by cveId OR search by keyword/cpeName/cvssV3Severity/date range — each row JOINED with its CISA KEV status. Returns { results:[{ cveId, vulnStatus, rejected, published, lastModified, description, cvssMetrics:[{version,source,type,baseScore,baseSeverity,vectorString,exploitabilityScore,impactScore}], primaryCvss:{version,baseScore,baseSeverity,type}|null, cwes, references, kev }] } + honest _meta. Optional kevOnly, resultsPerPage (≤2000, def 50), startIndex. CVSS HONESTY: every ^cvssMetric key (V2/V30/V31/V40) is its own element — versions never conflated; V2 baseSeverity reads from metric level; primaryCvss is highest-version, type:Primary preferred but FALLS BACK to highest Secondary (real CNA score never dropped), null ONLY when no CVSS exists — base scores null-never-0. KEV HONESTY: kev is {listed:true,dateAdded,dueDate,ransomware,requiredAction,catalogVersion} | {listed:false,note} | {listed:null,status:'unavailable'}; not-listed ≠ safe (absence is NOT a clearance); if KEV catalog cannot load, kev.listed degrades to NULL (never false) with fieldsUnavailable:['kev']; a kevOnly filter during KEV outage THROWS. PAGINATION from NVD EXACT totalResults (never page length). Genuine totalResults:0 → honest found:false; 403/429 → rate_limited THROWS with NVD_API_KEY tier disclosure; 404/5xx/timeout/off-host THROW. Optional free NVD_API_KEY (env) lifts the rate — sent ONLY in the apiKey header.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cveIdNoExact CVE identifier CVE-YYYY-NNNN (^CVE-\d{4}-\d+$, validated client-side). Exact-lookup mode; a malformed cveId is rejected (invalid_input) — a malformed cveId 404s upstream. At least one of cveId/keyword/cpeName/cvssV3Severity/a date range is REQUIRED.
cpeNameNoA CPE 2.3 formatted string to match affected products (cpe:2.3:[aho]:… — e.g. cpe:2.3:a:apache:log4j:2.14.1:*:*:*:*:*:*:*). Non-CPE input is rejected (invalid_input).
kevOnlyNoWhen true, return ONLY rows listed in the CISA KEV catalog. ★If the KEV catalog cannot be loaded, this THROWS (a KEV-membership filter is unanswerable without a loaded catalog) — it NEVER returns a silently-empty set (which would falsely read as 'none on the mandatory-remediation list').
keywordNoFree-text keyword search (NVD keywordSearch) over CVE descriptions (e.g. 'log4j', 'apache struts'). Control chars stripped, length-capped; rides only as a query param (SSRF-safe).
pubEndDateNoPublication-date window END (ISO YYYY-MM-DD). Paired with pubStartDate.
startIndexNoZero-based page offset (default 0). Pagination derives from NVD's exact totalResults, never the page length.
pubStartDateNoPublication-date window START (ISO YYYY-MM-DD). PAIRED with pubEndDate (both required together — NVD 404s a lone bound). A span >120 days is clamped forward to 120 days BEFORE the request and disclosed.
cvssV3SeverityNoFilter to a CVSS v3 base severity band (LOW|MEDIUM|HIGH|CRITICAL).
lastModEndDateNoLast-modified window END (ISO YYYY-MM-DD). Paired with lastModStartDate.
resultsPerPageNoRows per page (default 50, max 2000 — NVD's cap). Over-cap is refused, never silently clamped.
lastModStartDateNoLast-modified window START (ISO YYYY-MM-DD). PAIRED with lastModEndDate (both required together). A span >120 days is clamped + disclosed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.12.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say readOnlyHint=true and openWorldHint=true; the description carries a huge amount of behavioral disclosure: CVSS version-conflation rules, primaryCvss fallback behavior, KEV degradation to null, kevOnly throwing during KEV outage, NVD-exact pagination, honest found:false, rate-limit/403/429 throws, and API-key header behavior. This far exceeds what annotations provide and never contradicts them.

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?

Although long, the description is extremely dense and structured: purpose and modes first, then return shape, then explicit honesty guarantees, pagination, errors, and auth. Every sentence conveys a distinct operational fact; the length is justified by the tool's 11-parameter complexity and no output schema.

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 tool with no output schema, the description is exceptionally complete: it specifies the full return object, error behavior, rate-limit handling, degraded KEV semantics, pagination source, and auth protocol. An agent has enough context to select the tool, construct valid parameters, and anticipate edge cases.

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

Parameters5/5

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

Schema coverage is 100%, which sets a baseline of 3, but the description adds substantial semantics beyond the schema: kevOnly's throw-on-outage behavior, resultsPerPage over-cap refusal rather than clamping, startIndex pagination from NVD exact totalResults, date-window pairing/clamping, keyword sanitization, and cveId validation. These are meaningful behavioral additions to all major parameters.

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 opens with a specific verb and resource: 'Look up NIST NVD CVE records' via the NVD CVE API 2.0. It clearly narrows the scope to exact-by-cveId or search-by-keyword/cpeName/severity/date-range modes, and emphasizes the distinct CISA KEV join, which separates it from the sibling cisa_kev_lookup.

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

Usage Guidelines4/5

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

The description gives strong usage context: exact lookup versus keyword/CPE/severity/date-range search, plus optional kevOnly and pagination. It does not explicitly name alternative sibling tools or say when NOT to use this tool versus cisa_kev_lookup, so it falls just short of the 5-level explicit when/when-not guidance.

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

Deploy Server

Other Tools