MCP Server

Active

MIT

ContrastAPI MCP Server

com.contrastcyber/api

55 security tools for AI agents: CVE/KEV lookup, vulnerability assessment, threat intelligence, and OSINT—free, no API key.

Repository Registry

What is the ContrastAPI MCP server?

ContrastAPI is an MCP server providing 55 security intelligence tools for AI agents, grounded in authoritative sources like NVD, CISA KEV, FIRST EPSS, and MITRE frameworks. It enables vulnerability lookup, threat assessment, domain/IP investigation, and code-security checks without requiring signup or API keys.

ContrastAPI gives AI agents access to comprehensive security intelligence across CVE/KEV/CWE databases, MITRE ATLAS and D3FEND frameworks, Sigma rules, email security posture (SPF/DMARC), domain and IP investigation, IOC enrichment, and web intelligence. Use it to ground security decisions in authoritative data, assess exploit probability via EPSS scores, and investigate attack surface with live web intelligence.

How to install ContrastAPI

Copy-paste configuration for popular MCP clients.

transport: http

Config generated by PluginBench — verify against the source before use.

~/.cursor/mcp.json

{
  "mcpServers": {
    "api": {
      "url": "https://api.contrastcyber.com/mcp/"
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

CVE lookup — Query NVD for vulnerability details, EPSS exploit probability, and composite risk scoring
KEV detail — Check CISA Known Exploited Vulnerabilities catalog
CWE lookup — Retrieve Common Weakness Enumeration details
EPSS scoring — Exploit Prediction Scoring System probability assessment
Domain investigation — Analyze domain security posture and configuration
IP investigation — Query IP reputation and threat intelligence
IOC enrichment — Investigate indicators of compromise
Code security checks — Assess code for security vulnerabilities
Sigma rules — Query and apply Sigma detection rules
Email SPF/DMARC — Verify email authentication and security posture
MITRE ATLAS — Browse MITRE ATLAS adversary tactics and techniques
MITRE D3FEND — Access MITRE D3FEND defensive countermeasures
Web intelligence tools — robots.txt, redirect chains, email verification, brand assets, SEO audit, geo audit

Use cases

Look up CVE details with EPSS exploit probability and risk scores to prioritize patching
Check if a vulnerability is in CISA's Known Exploited Vulnerabilities catalog for immediate threat assessment
Investigate domain and IP reputation to assess attack surface and threat landscape
Verify email authentication (SPF/DMARC) to evaluate email security posture
Enrich indicators of compromise (IOCs) with threat intelligence from authoritative sources

ContrastAPI MCP server FAQ

What is ContrastAPI?

ContrastAPI is a free MCP server with 55 security tools that give AI agents access to vulnerability databases (CVE/KEV/CWE), MITRE frameworks, Sigma rules, and threat intelligence—all grounded in authoritative sources like NVD and CISA.

Is ContrastAPI free?

Yes, ContrastAPI is completely free. No signup, no API key required. All 55 tools are available immediately.

How do I install ContrastAPI in Claude Desktop?

Download the `.mcpb` file from the latest GitHub release and double-click it, or go to Claude Desktop Settings → Extensions → Install Extension. Alternatively, use the JSON config with `mcp-remote` for any MCP client.

What authentication does ContrastAPI require?

None. ContrastAPI requires no API key, signup, or authentication. It works out of the box.

Can I use ContrastAPI for vulnerability assessment?

Yes. You can look up CVE/KEV/CWE details, retrieve EPSS exploit-probability scores, and calculate composite risk scores to prioritize vulnerabilities.

What sources does ContrastAPI use?

ContrastAPI pulls from authoritative sources including NVD, CISA KEV, FIRST EPSS, MITRE ATLAS, MITRE D3FEND, and live web intelligence APIs.

README (reference)

Source of truth, from the repository.

ContrastAPI — 55 Security Tools + 7 MCP Resources for AI Agents

Security intelligence, built for AI agents. Give your agent grounded answers about vulnerabilities, threats, and attack surface — backed by authoritative sources (NVD, CISA KEV, FIRST EPSS, MITRE ATLAS & D3FEND), never guesswork. CVE/KEV/CWE lookup with EPSS exploit-probability and composite risk scoring, domain & IP investigation, IOC enrichment, code-security checks, and live web intelligence. 55 tools, 7 Resources, and 3 Prompts — free, no API key, no signup.

中文 · Live: api.contrastcyber.com

Documentation

API Documentation — REST reference: 60+ endpoints, authentication, rate limits, token costs, and response envelope.
MCP Documentation — MCP tool-selection guide, 7 Resources, 3 Prompts, and copy-paste agent prompts.

Setup (MCP)

Any MCP client

{
  "mcpServers": {
    "contrastapi": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.contrastcyber.com/mcp/"]
    }
  }
}

Restart your agent. Other clients (Python SDK, Node SDK, cURL, VS Code): mcp-setup · quickstart

Claude Desktop — one-click extension

Grab the .mcpb file from the latest release and double-click it (or Claude Desktop → Settings → Extensions → Install Extension…). No signup, no API key — all 55 tools ready immediately.

SDKs

pip install contrastapi      # Python 3.10+ — sync + async, typed responses, shortcut helpers
npm install contrastapi      # Node 14+ — concrete TypeScript types, 14 namespaces

Both SDKs cover every HTTP endpoint and MCP tool — CVE/KEV/CWE, ATLAS, D3FEND, Sigma rules, email security posture, domain, IP, IOC, code security, and web intelligence — with wire-exact response shapes and a typed exception hierarchy that mirrors the API error envelope. They also expose MCP Resources for browsing the ATLAS, D3FEND, and CWE catalogs (see docs/MCP_Documentation.md) and a conditional triage Prompt (see docs/MCP_Documentation.md#contrast-triage). Web-intelligence tools — robots_txt, redirect_chain, email_verify, brand_assets, seo_audit, geo_audit — ship with an explicit ethical floor: per-target throttling, robots.txt respected, no SMTP probing.

Links

OpenAPI: openapi.json

<details> <summary>Also available on</summary>

Smithery · npm · VS Code Marketplace · Awesome OSINT MCP · RapidAPI

</details> <details> <summary>Multi-agent verdict metadata</summary>

Responses include a verdict block — deterministic, falsifiable_fields, data_age_seconds, sources_queried / sources_unavailable, completeness — so a verifier agent can independently re-derive specific fields from the upstream authority (NVD, RDAP, CT logs, URLhaus). Probe GET /v1/capabilities for "verdict_metadata": true.

CVE responses also embed next_calls: list[PivotHint] — {tool, input, reason} triples that suggest the next MCP tool to call (e.g. kev_detail when kev.in_kev=true, cwe_lookup when cwe_id is set). Agents chain workflows without manual prompting.

</details>

MIT

Related MCP servers

MDX

View repository →

com.conveyancingfeesaustralia/site

Conveyancing Fees Australia: the site's own MCP server — enquiry (enquiry = a human handoff, not...