Skip to main content
Glama

gapup-mcp

by io.github.getgapup

cve_security_lookup

Read-only

Look up CVE vulnerability data for enterprise security teams, DevSecOps and SOC analysts. Supports two modes: exact CVE ID lookup (e.g. 'CVE-2024-3094') or keyword search by product/vendor (e.g. 'openssl', 'Apache Tomcat'). Cross-references four authoritative keyless sources: NVD NIST (official CVE database, CVSS v3 scores, affected CPEs), CISA KEV (Known Exploited Vulnerabilities catalog — exploit_in_wild flag), EPSS FIRST (exploit probability 0-1), GitHub Security Advisories (ecosystem-specific: npm/pypi/maven). Returns structured vulnerability records with CVSS v3 scores, affected product version ranges, CWE weakness classification, references and exploitation status. Signals engine produces P0/P1/P2 alerts: P0=CVSS>=9 + active exploitation, P1=CVSS>=7 or EPSS>=70%, P2=CWE pattern clusters. Relevant for EU NIS2 and DORA supply chain risk obligations. Optional env: NVD_API_KEY (raises NVD rate-limit 5→50 req/30s), GITHUB_TOKEN (raises GHSA GraphQL rate-limit). Cache TTL 6h. SLA <=25s p95.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoOverride auto-detection: "lookup" for exact CVE ID, "search" for product/vendor keyword.
asyncNoIf true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
queryYesCVE ID (e.g. "CVE-2024-3094") or product/vendor keyword (e.g. "openssl", "Apache Tomcat"). Mode is auto-detected from the CVE-YYYY-XXXXX pattern.
max_resultsNoMaximum number of vulnerabilities to return (default 20, max 50).
severity_minNoMinimum CVSS v3 severity to include in results (default: no filter).
published_afterNoISO date YYYY-MM-DD — only include CVEs published after this date. Defaults to 365 days ago for search mode.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeYes
queryYes
statusYes
signalsYes
sourcesYes
quality_scoreYes
vulnerabilitiesYes

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=true, destructiveHint=false), the description provides rich behavioral context: it aggregates data from NVD, CISA KEV, EPSS, and GitHub Security Advisories; generates P0/P1/P2 alerts with specific thresholds; mentions cache TTL (6h), SLA (≤25s p95), and optional environment variables for rate limits. This significantly exceeds what annotations convey and helps the agent predict side effects and performance.

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?

The description is dense but logically structured: purpose, modes, data sources, output, alert logic, regulatory relevance, operational details. Every sentence adds value, though the regulatory mention and detailed source enumeration could be trimmed without losing core guidance. It is well-organized and front-loaded with the primary purpose.

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?

Given the tool's complexity (two modes, four sources, alert engine, async option, output schema exists), the description covers nearly all operational aspects: how queries are interpreted, what information is returned, alert thresholds, caching, rate limits, and latency. The description is comprehensive enough for an agent to select and invoke it appropriately.

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 coverage is 100% and each parameter already has a meaningful description (e.g., mode override, async behavior, query format, max_results, severity filter, published_after). The tool description adds context about sources and alerts but does not elaborate on parameter semantics beyond the schema. Thus, the baseline of 3 applies.

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 clear verb and resource: 'Look up CVE vulnerability data.' It distinguishes itself from siblings by specifying two modes (exact CVE ID lookup and keyword search) and detailing cross-referencing of four authoritative sources. This makes its purpose unambiguous and sets it apart from related tools like vulnerability scanners or patch prioritizers.

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 identifies target users (enterprise security teams, DevSecOps, SOC analysts) and regulatory contexts (EU NIS2, DORA), implying when it is appropriate. It clearly states the two input modes with examples, which guides usage. However, it does not explicitly contrast with sibling tools or list exclusions, so agents might not know when to choose this over alternatives like vuln_patch_priority_engine.

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

All gapup-mcp toolsInspect
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

C2.4/5.0
Disambiguation1/5

Over 50 tools share the identical template 'Gapup agent-payable C-suite expertise' with similar French descriptions and reference cases, making their boundaries indistinguishable. Clusters like competitor_intel, competitive_deep_dive, competitor_moves, competitor_profiles, competitor_pricing_radar, competitor_pricing_scrape, and competitor_recommendations heavily overlap in purpose.

Naming Consistency1/5

Names are chaotic: mix of French and English, snake_case and camelCase, verb_noun, noun, and adjective forms with no uniform pattern. Examples like 'bp_narratif', 'content_enrichment', 'ai_governance_full_report_async', and 'job_result' show no coherent naming convention.

Tool Count1/5

271 tools is far beyond any reasonable MCP server scope, creating an overwhelming selection burden for agents. This count vastly exceeds the 25+ threshold for 'too many' and makes navigation impractical.

Completeness2/5

While the server covers many business domains, it lacks lifecycle operations (e.g., no update/delete tools for the deliverables it generates) and the input specifications are vague ('documented case fields' without documentation), creating functional dead ends. The sheer breadth does not compensate for these gaps.

Resources