Skip to main content
Glama
Vulnerability Registry MCP Server

Vulnerability Registry MCP Server

by orcohen5

Vulnerability Registry MCP Server

Author: Or Cohen

An MCP (Model Context Protocol) server that wraps a legacy vulnerability database and exposes it as tools for any MCP-compatible LLM client. Built as a smart access layer over custom pipe-delimited data files, enabling security analysts to query vulnerabilities using natural language.

Quick Start

Prerequisites

  • Node.js 18+

  • Claude Desktop (or any MCP-compatible client)

Setup

git clone https://github.com/orcohen5/vulnerability-registry.git
cd vulnerability-registry
npm install
npm run build

Connect to Claude Desktop

Add to your Claude Desktop config (%APPDATA%\Claude\claude_desktop_config.json on Windows, ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "vulnerability-registry": {
      "command": "node",
      "args": [
        "<FULL_PATH>/vulnerability-registry/dist/index.js",
        "<FULL_PATH>/vulnerability-registry/data"
      ]
    }
  }
}

Replace <FULL_PATH> with the absolute path to the cloned repository.

Restart Claude Desktop, then ask:

"What MCP tools do you have for vulnerabilities?"

Tool Discovery Claude Desktop discovering all 6 vulnerability registry tools

Related MCP server: pentestMCP

Available Tools

Tool

Description

Key Parameters

Example Query

list_vendors

List all registered software vendors

category (optional)

"Show me all open source vendors"

get_vendor

Find a vendor by ID or name

vendor_id, name

"Find the vendor ID for Linux Kernel"

search_vulnerabilities

Search with flexible filters

severity, status, min_cvss, keyword, published_after

"Show critical open vulnerabilities"

get_vulnerability

Get full CVE details

cve_id

"What is the CVSS score of Log4Shell?"

get_vulnerability_stats

Aggregate statistics

vendor_id (optional)

"How many vulnerabilities by severity?"

get_vendor_risk_summary

Vendor risk profile

vendor_id

"Show me Microsoft's risk profile"

Example Queries

"How many critical vulnerabilities are still open?"

Uses search_vulnerabilities with severity: "critical" and status: "open".

Critical Open Vulnerabilities

"What is the CVSS score of Log4Shell?"

Uses get_vulnerability with cve_id: "CVE-2021-44228".

Log4Shell CVSS

"Show me the risk profile for Microsoft"

Uses get_vendor_risk_summary with vendor_id: "V1".

Microsoft Risk Profile

"Which vulnerabilities were found in Linux Kernel after 2022?"

This query demonstrates multi-tool orchestration — Claude first calls list_vendors to resolve "Linux Kernel" to vendor ID V5, then calls search_vulnerabilities with vendor_id: "V5" and published_after: "2022-01-01".

Linux Kernel Multi-Tool Query

Architecture

┌─────────────────┐     ┌──────────────┐     ┌──────────────┐
│  Claude Desktop │────▶│  MCP Server  │────▶│  Data Files  │
│  (MCP Client)   │◀────│  (stdio)     │◀────│  (.db)       │
└─────────────────┘     └──────┬───────┘     └──────────────┘
                               │
                    ┌──────────┼──────────┐
                    ▼          ▼          ▼
               tools.ts   repository.ts  parser.ts
              (MCP layer)  (query engine) (file reader)

The codebase follows a strict three-layer separation:

  • parser.ts — Reads the custom pipe-delimited format dynamically. Knows nothing about MCP.

  • repository.ts — In-memory data store with indexed Maps for O(1) lookups. Knows nothing about MCP.

  • tools.ts — Registers MCP tools using the high-level McpServer API. Translates between MCP and the repository.

This means swapping the data source (files → database) requires changing only parser.ts, with zero changes to the MCP layer.

Design Decisions

Dynamic metadata parsing — The file parser reads column names from the # FORMAT: header at runtime rather than hardcoding field positions. Combined with version checking (# VERSION: 1.0), this ensures the server can detect and warn about format changes without code modifications.

Repository pattern with in-memory indexing — Data is loaded once at startup and indexed into multiple Maps (vendorById, vulnByCveId, vulnsByVendor, vulnsBySeverity, vulnsByStatus). Primary lookups are O(1). Filtered searches start from the smallest indexed subset and intersect, making combined queries efficient even at scale.

High-level McpServer API — Uses McpServer.registerTool() with Zod schemas for type-safe input validation, rather than the low-level Server class with manual JSON Schema definitions and request routing.

Flexible search with optional filters — search_vulnerabilities accepts all parameters as optional, allowing any combination. One tool handles queries from "show all critical" to "find Linux CVEs from 2023 with CVSS above 8". Results are always sorted by CVSS score (highest first) so the most severe issues appear first.

Enriched responses — get_vulnerability returns the full vendor object alongside the CVE data. get_vendor_risk_summary includes the list of open vulnerabilities. This reduces the number of tool calls the LLM needs to answer common questions.

Strict type safety — Severity and Status are union types derived from as const arrays, with runtime type guards (isSeverity, isStatus). The same source-of-truth arrays feed both TypeScript types and Zod enum validators.

Known Data Anomalies

While working with the source data files, I identified at least one attribution inconsistency: CVE-2024-21762 (Fortinet SSL VPN OOB) is mapped to vendor V4 (Google) in vulnerabilities.db, although this is a Fortinet vulnerability. The server faithfully returns the data as stored — correcting source data is out of scope for a read-only query layer. In a production system, I would add a data validation step at load time to flag such inconsistencies for human review, possibly by cross-referencing the NVD API for canonical vendor attribution.

What I'd Build With More Time

  • SQLite/PostgreSQL persistence — Replace in-memory storage for datasets that exceed available RAM, with connection pooling for concurrent access.

  • Pagination — Add limit/offset parameters to search_vulnerabilities for large result sets.

  • Fuzzy text search — Levenshtein distance matching on vulnerability titles for typo-tolerant queries.

  • NVD API integration — Automatic CVE data updates from NIST's National Vulnerability Database.

  • MCP Resources — Expose raw data files as MCP Resources for direct LLM access when full-text context is needed.

  • Structured logging & observability — JSON-formatted logs with correlation IDs for debugging tool call chains.

  • Authentication & rate limiting — Protect the server in shared deployment scenarios.

  • CI/CD pipeline — GitHub Actions running lint, type-check, and tests on every push.

Tech Stack

Component

Choice

Language

TypeScript (ES2022, Node16 modules)

MCP SDK

@modelcontextprotocol/sdk — McpServer high-level API

Validation

Zod

Transport

stdio

Build

tsc

Tests

Vitest

Testing

npm test        # Run all tests (30 tests across parser + repository)
npm run build   # Compile TypeScript
npm start       # Start the MCP server (stdio mode)

Available Tools

6 tools
get_vendorGet VendorA

Get details about a specific vendor by their ID (e.g. 'V1') or by name (case-insensitive partial match, e.g. 'linux' will match 'Linux Kernel Organization'). Use this to find a vendor's ID before querying their vulnerabilities.

Inputs: vendor_id, name.

get_vendor_risk_summaryGet Vendor Risk SummaryA

Get a comprehensive risk profile for a specific vendor. Shows total vulnerabilities, open vs patched breakdown, severity distribution, highest CVSS score, and lists all currently open vulnerabilities. Ideal for vendor risk assessment.

Inputs: vendor_id (required).

get_vulnerabilityGet VulnerabilityA

Get full details of a specific vulnerability by its CVE ID (e.g. 'CVE-2021-44228') or internal ID (e.g. 'CVE001'). Returns the vulnerability with its associated vendor information.

Inputs: cve_id (required).

get_vulnerability_statsGet Vulnerability StatisticsA

Get summary statistics about vulnerabilities. Shows counts by severity, status, vendor, and year, plus CVSS score metrics (average, min, max). Optionally scope stats to a specific vendor.

Inputs: vendor_id.

list_vendorsList VendorsB

List all registered software vendors in the vulnerability database. Optionally filter by category (e.g. 'Software', 'Open Source').

Inputs: category.

search_vulnerabilitiesSearch VulnerabilitiesA

Search and filter vulnerabilities with flexible criteria. All filters are optional and can be combined. Returns matching vulnerabilities sorted by CVSS score (highest first). Use for questions like 'show critical open vulnerabilities' or 'find CVEs published after 2023'.

Inputs: vendor_id, severity, status, min_cvss, +4 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: get_vendor retrieves vendor details, get_vendor_risk_summary provides risk profiles, get_vulnerability fetches specific vulnerability data, get_vulnerability_stats offers statistical summaries, list_vendors enumerates vendors, and search_vulnerabilities enables filtered searches. The descriptions explicitly differentiate their functions, preventing agent misselection.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern using snake_case, with verbs like 'get', 'list', and 'search' clearly indicating actions. This uniformity makes the tool set predictable and easy to navigate, enhancing agent usability without any naming deviations.

    Tool Count5/5

    With 6 tools, the server is well-scoped for a vulnerability registry, covering core operations such as retrieving vendors and vulnerabilities, assessing risks, and generating statistics. Each tool serves a unique and necessary function, avoiding bloat or gaps for this domain.

    Completeness4/5

    The tool set provides comprehensive coverage for querying and analyzing vulnerability data, including CRUD-like operations for vendors and vulnerabilities, risk assessment, and statistical insights. A minor gap exists in the lack of tools for creating, updating, or deleting entries, but this is reasonable for a read-only registry focused on data retrieval and analysis.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that integrates various penetration testing tools, enabling security professionals to perform reconnaissance, vulnerability scanning, and API testing through natural language commands in compatible LLM clients like Claude Desktop.
      7
      -
    • F
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that exposes over 20 standard penetration testing utilities, such as Nmap, SQLMap, and OWASP ZAP, as callable tools for AI agents. It enables natural language control over complex security workflows for automated and interactive penetration testing.
      117
      -
    • A
      license
      A
      quality
      B
      maintenance
      An MCP server for vulnerability management that provides tools for automated severity and CWE classification using NLP models. It enables AI agents to query the Vulnerability Lookup API for detailed CVE information and search for security vulnerabilities across various sources.
      16
      43
      AGPL 3.0
    • A
      license
      A
      quality
      C
      maintenance
      Unifies NVD, EPSS, CISA KEV, GitHub Advisory, and OSV into a single MCP server, enabling AI agents to query vulnerability intelligence conversationally with 23 tools for incident response, prioritization, dependency audits, and threat monitoring.
      41
      292 npm
      30
      MIT