Vulnerability Registry MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Vulnerability Registry MCP Server What is the CVSS score and status of CVE-2021-44228?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Vulnerability Registry MCP Server
A TypeScript MCP server that exposes a legacy, file-based vulnerability registry to MCP-compatible LLM clients. The server parses versioned pipe-delimited files at startup, validates referential integrity, builds in-memory indexes, and exposes focused tools for CVE lookup, search, vendor navigation, and aggregate statistics.
Architecture
Legacy DB files
↓
Version-aware parser
↓
Validated domain models
↓
In-memory registry and indexes
↓
MCP tools over stdioThe parser reads FORMAT dynamically, so the implementation does not depend on a fixed column order. Version-specific parsing is selected through a parser registry. Raw parsing and domain mapping are deliberately separated: the parser understands file structure, while mappers validate business meaning such as CVE syntax, CVSS range, status, severity, and dates.
Related MCP server: vulnerability-registry-mcp
Requirements
Node.js 20 or newer
npm
Install and run
npm ci
npm run build
npm startDevelopment mode:
npm run devAll logs are written to stderr; stdout remains reserved for MCP stdio traffic.
Configuration
Optional environment variables:
VENDORS_DB_PATHVULNERABILITIES_DB_PATHDEFAULT_PAGE_SIZE(default: 20)MAX_PAGE_SIZE(default: 100)
Tools
get_vulnerability
Retrieves one vulnerability by exact CVE identifier.
Example: What is the CVSS score and status of CVE-2021-44228?
search_vulnerabilities
Searches and filters by free text, vendor, severity, status, CVSS range, publication dates, sorting, and pagination.
Example: Which open Linux Kernel vulnerabilities have CVSS 7 or higher?
search_vendors
Finds vendors by name, category, or headquarters and includes useful counts.
get_vendor_overview
Returns vendor details, aggregate statistics, and the five most recent vulnerabilities.
get_vulnerability_statistics
Returns counts by status and severity plus CVSS minimum, maximum, and average without returning every matching row.
Example: How many critical vulnerabilities are still open?
Validation policy
Startup fails when data cannot be trusted, including:
unsupported database version;
missing metadata or required columns;
malformed row field counts;
invalid CVE, CVSS, status, severity, date, or founded year;
duplicate vendor IDs, vulnerability IDs, or CVE IDs;
vulnerability references to missing vendors.
This fail-fast policy avoids plausible but incomplete security answers.
Performance
The files are loaded once at startup. Exact lookups and joins use:
vendorsById;vulnerabilitiesByCve;vulnerabilitiesByVendorId.
For the expected scale of thousands of records, compound text filtering remains a simple in-memory scan. This is easier to reason about and maintain than introducing a search dependency prematurely. Pagination and deterministic sorting prevent oversized or unstable responses.
affected_versions is intentionally kept as free text. The source format does not define a formal version-range grammar, so the server supports text search but does not claim semantic range evaluation.
Quality checks
npm run typecheck
npm run lint
npm test
npm run build
npm run checkTo inspect the MCP server interactively:
npm run inspectClaude Desktop configuration
Build first, then add an absolute path:
{
"mcpServers": {
"vulnerability-registry": {
"command": "node",
"args": ["/absolute/path/to/vulnerability-registry-mcp/dist/src/index.js"]
}
}
}Design decisions
Modular monolith rather than a framework-heavy application.
No dependency-injection container; dependencies are passed explicitly from the composition root.
No repository interface until a second persistence implementation exists.
MCP handlers contain transport concerns only; all querying lives in
VulnerabilityRegistry.Errors are typed and translated to safe MCP error payloads without leaking stack traces.
Both text
contentand machine-readablestructuredContentare returned.
With more time
I would add atomic hot reload when source files change, richer full-text indexing, support for additional format versions, audit logging, operational metrics, and a dedicated natural-language agent client. For a remotely hosted deployment, I would add authentication, authorization, rate limiting, and Streamable HTTP transport.
Production-oriented AI agent stack
This repository now includes an optional end-to-end stack:
Open WebUI
↓ OpenAI-compatible HTTP (/v1/chat/completions)
TypeScript Agent Service
↓ MCP Streamable HTTP
Vulnerability Registry MCP Server
↓
Validated in-memory registry loaded from the legacy .db filesThe original stdio entry point remains available for local MCP clients. The remote entry point is src/http.ts, and the OpenAI-compatible agent entry point is src/agent/http-server.ts.
Why the Agent Service exists
Open WebUI is the user interface, not the MCP client that contains the application-specific orchestration policy. The Agent Service:
exposes
/v1/modelsand/v1/chat/completions, which Open WebUI understands;connects to the MCP server and discovers its tools dynamically;
gives those tool schemas to an OpenAI-compatible model provider;
executes requested MCP tool calls;
returns the final grounded answer to Open WebUI;
keeps model-provider credentials out of the browser;
applies authentication, timeouts, request-size limits and a maximum number of tool rounds.
Important: ChatGPT Plus and API billing
A ChatGPT Plus subscription is separate from OpenAI API usage. To use an OpenAI model through this Agent Service, create an API key and enable API billing separately. The Agent Service is provider-neutral: LLM_BASE_URL, LLM_API_KEY and LLM_MODEL can point to another OpenAI-compatible provider instead.
HTTP MCP entry point
Run the remote MCP server:
npm run build
MCP_API_KEY=local-mcp-key npm run start:httpEndpoints:
POST /mcp— stateless MCP Streamable HTTP transportGET /health— process livenessGET /ready— verifies that the registry files can be loaded and validated
Environment variables:
Variable | Default | Purpose |
|
| Bind address |
|
| HTTP port |
| unset | Optional bearer token required by |
Agent Service
Run it after the HTTP MCP server is available:
LLM_API_KEY=replace-me \
MCP_URL=http://localhost:8080/mcp \
MCP_API_KEY=local-mcp-key \
AGENT_API_KEY=local-agent-key \
npm run start:agentMain environment variables:
Variable | Default | Purpose |
|
| Agent HTTP port |
| unset | Bearer token accepted from Open WebUI |
|
| Model name shown in Open WebUI |
|
| Remote MCP endpoint |
| unset | Token sent to the MCP server |
|
| OpenAI-compatible provider base URL |
| required | Provider API key |
|
| Provider model used for reasoning/tool calls |
|
| Prevents unbounded tool loops |
|
| Provider request timeout |
Docker Compose
Copy the example environment file and replace every placeholder:
cp .env.example .envOn PowerShell:
Copy-Item .env.example .envStart the full stack:
docker compose up --buildOpen WebUI at http://localhost:3000. On first launch, create the admin user. Then open:
Admin Settings → Connections → OpenAI → Add ConnectionConfigure:
URL: http://agent:8081/v1
API key: the value of AGENT_API_KEY in .env
Model: vulnerability-agentThe Docker network resolves the hostname agent from the Open WebUI container. Do not use localhost:8081 in this screen because, inside the Open WebUI container, localhost refers to Open WebUI itself.
Why PostgreSQL is included
PostgreSQL is not needed for the vulnerability registry itself in the current assignment. The legacy files are loaded once, validated and indexed in memory, which is appropriate for the stated scale of thousands of records.
PostgreSQL is included for Open WebUI persistence. It stores application state such as:
users and authentication records;
chat history;
saved settings and model connections;
permissions and shared UI objects.
For one local demo instance, Open WebUI can use its built-in SQLite database and PostgreSQL may be removed from docker-compose.yml. For a production deployment with multiple workers or replicas, PostgreSQL is the safer choice because SQLite does not support concurrent writes from several application instances and should not be placed on shared network storage.
The Agent Service itself is deliberately stateless. It does not need PostgreSQL merely to call MCP tools. A future version could add agent-owned tables for audit records, feedback, conversation checkpoints, usage accounting or idempotency, but those concerns should be added only when required rather than coupling them to the vulnerability data.
Production notes
Pin the Open WebUI image to a tested release before deployment; do not use a floating development tag.
Replace all example secrets and store them in a secret manager in hosted environments.
Terminate TLS at a reverse proxy or ingress and do not expose plain HTTP publicly.
Add rate limiting at the gateway/ingress layer.
The HTTP MCP server is stateless, so replicas can be scaled horizontally without session affinity.
The current streaming response is OpenAI-compatible but buffered: the Agent completes its tool loop before emitting one SSE content chunk. Token-by-token provider streaming can be added later without changing the Open WebUI contract.
Available Tools
5 toolsget_vendor_overviewGet vendor overviewA
Return one vendor, aggregate vulnerability statistics, and its five most recent vulnerabilities. Use after identifying a vendor ID.
Inputs: vendorId (required). Returns: vendor, statistics, recentVulnerabilities
get_vulnerabilityGet vulnerabilityA
Retrieve one vulnerability by its exact CVE identifier. Use for score, status, vendor, affected versions, title, or publication date of a specific CVE.
Inputs: cveId (required). Returns: vulnerability
get_vulnerability_statisticsGet vulnerability statisticsA
Count and summarize vulnerabilities without returning every matching record. Use for questions such as how many critical vulnerabilities are open.
Inputs: status, severity, vendorId, vendorName, +2 more. Returns: cvss, total, byStatus, bySeverity
search_vendorsSearch vendorsA
Find vendors by name, category, or headquarters and return vulnerability counts.
Inputs: limit, query, offset. Returns: items, limit, total, offset, +1 more
search_vulnerabilitiesSearch vulnerabilitiesA
Search and filter vulnerabilities by text, vendor, severity, status, CVSS score, or publication date. Use this for lists of matching CVEs.
Inputs: limit, query, offset, sortBy, +9 more. Returns: items, limit, total, offset, +1 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct operation: get_vulnerability for a specific CVE, search_vulnerabilities for filtered lists, search_vendors for vendor lookup, get_vendor_overview for aggregate vendor data, and get_vulnerability_statistics for counts. There is no meaningful overlap between any pair of tools.
All tool names follow a consistent verb_noun pattern using lowercase and underscores, with verbs limited to 'get' and 'search'. The naming clearly indicates whether a tool returns a single entity, a list, or statistics.
With 5 tools, the server is well-scoped for a vulnerability registry query interface. Each tool covers a distinct need without redundancy or bloat, fitting comfortably in the ideal 3-15 range.
The tool set provides complete read-only coverage for a vulnerability registry: individual CVE lookup, flexible searching, vendor discovery, vendor-specific aggregation, and vulnerability statistics. No obvious gaps exist for the apparent domain.
Maintenance
Related MCP Connectors
ZEN SecDB MCP server for CVE intelligence, CVSS/EPSS scoring, advisories, SSVC, and package audits.
The main MCP server has 10 tools, including six public, read-only CVE tools, site search and page reading. CVE results include source software/version evidence and available CISA KEV and dated FIRST EPSS data. The separate request_security_test action requires an agent key, consent and authorization. A no-account, read-only CVE-only endpoint is https://excessionlabs.ai/mcp/cve. Docs: https://excessionlabs.ai/cve-intelligence/.
Search and audit NIST NVD CVEs by keyword, severity, CWE, CISA KEV status, and CPE.
Read-only vulnerability intelligence: CVEs, exploitation evidence, fixes and product matches.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server that provides tools to search, filter, and retrieve CVE data from the NVD API, including by ID, keyword, severity, and recency.4293 PyPIMIT
- FlicenseNot gradedqualityDmaintenanceEnables security analysts and risk managers to query a legacy CVE registry via natural language, providing tools for searching vulnerabilities, retrieving details, and obtaining statistics.-
- AlicenseAqualityCmaintenanceEnables users to search and retrieve CVE records, CVE history, CPE Dictionary entries, and CPE match criteria through MCP tools, with local caching, pagination, and upstream rate-limit handling.10MIT
- FlicenseNot gradedqualityAmaintenanceEnables querying the CVE-Search API to browse vendors and products, retrieve vulnerabilities by vendor/product or CVE ID, fetch the latest CVEs with CAPEC/CWE/CPE details, and check database update status via MCP tools.-