Skip to content

Vulnetix MCP server

A hosted Model Context Protocol server giving any MCP client 31 tools over the Vulnetix VDB, plus local-workflow prompts, templates and views.

Updated 04 Nov 2026Markdown

The MCP server is for developers and security engineers who work through an AI coding agent and want vulnerability answers in that conversation: is this CVE exploited, is this package safe to install, which version fixes it. Your agent calls it as a tool. For the same data from a script or service, call the VDB API directly or use vulnetix vdb from the CLI. To control what your agents send to model providers, use the AI Firewall, which is a gateway rather than a data source.

The Vulnetix MCP server is a remote MCP endpoint that an AI coding agent calls for vulnerability data. It answers from the Vulnetix VDB, which aggregates CVE.org, NVD, VulnCheck, CISA KEV, GitHub and OSV advisories, EUVD and other sources. There is nothing to install: you add a URL and a header to your client.

URL     https://mcp.vulnetix.com/mcp
Header  Authorization: ApiKey <orgId>:<hex>

What the server exposes

Primitive Count Names Page
Tools 31 vulnetix_* and vdb_request Tool reference
Prompts 18 vulnetix_*, generated from the Pix skills Prompts
Agent Skills 18 skill://<name>/SKILL.md over io.modelcontextprotocol/skills Skills
Resource templates 5 vulnetix://vuln/{id}, vulnetix://vuln/{id}/full, vulnetix://kev/{id}, vulnetix://package/{ecosystem}/{name}, skill://{name}/{+path} Resources
App views 3 ui://vulnetix/kev-board, ui://vulnetix/triage-queue, ui://vulnetix/cve-card Apps

Server name vulnetix, version 0.1.0. Protocol revision 2026-07-28, with 2025-11-25 clients served on the same endpoint.

What it does and does not do

Does Does not
Look up an advisory: KEV status and due date, EPSS, SSVC, exploitation maturity, affected packages and routines Read, scan or upload your code. No tool accepts file content.
Count exploits per source and show sightings, IOCs and threat actors Apply a fix or edit a manifest
Score a package or purl before you install it, with a Safe Harbour version Run a scanner or an exploit
Return detection rules, workarounds, vendor advisories and VEX Remember anything between requests
Add an optional model-written analysis on Pro plans Supply a credential for you

Every prompt is a procedure your own agent runs locally with the Vulnetix CLI. See Local workflows.

Responses are shaped

A raw vdb-api record for CVE-2021-44228 is 2,606,571 bytes. vulnetix_vuln returns 10,613 bytes by default with every decision field kept, and the rest one resources/read away. See Response shaping.

Find the page for your task

I want to Read
Connect a client in two minutes Quickstart
Get the exact config for my client Clients
Look up a tool’s parameters Tool reference
Find which tool answers my question Tools by question
Follow a worked sequence, such as triaging one CVE Guides
Check what the server cannot do Limitations
Read short answers before I connect FAQ
Get a key from inside the agent Authentication
Find out why an exploit list is empty Plans and limits
Debug a -32602 or a 401 Troubleshooting
Run the agent in CI Agents in CI
Approve it for my organisation Security model
Product Runs Use it for
MCP server Hosted; you connect to it Vulnerability questions from any MCP client
Pix Inside your coding agent Local skills, hooks and slash commands
CLI Your machine and CI Scanning, SBOMs, fixes and deterministic gates

All three use one VDB and one credential.

Platform IaC

The MCP server has no config-as-code of its own: the only configuration is the client-side MCP entry described on each client page. The AI firewall’s allow and deny lists for MCP servers, tools and skills are AiGovernanceList documents. See the kind catalogue.

esc
↑ ↓ move↵ openSearches in your browser. A key like autonomy.max or a code like threshold_required jumps straight to it.