mcp-greynoise
# mcp-greynoise
[](https://www.npmjs.com/package/mcp-greynoise)
[](https://opensource.org/licenses/MIT)
MCP server for the [GreyNoise](https://greynoise.io) API — check if IP addresses are internet background noise or potentially targeted attacks.
## Quick Start
```bash
npx mcp-greynoise
```
That's it. Works out of the box with 10 lookups/day (no API key needed).
## What is GreyNoise?
GreyNoise collects and analyzes internet-wide scan traffic. It tells you:
- **Noise**: Is this IP mass-scanning the internet? (botnets, researchers, crawlers)
- **RIOT**: Is this IP a known benign service? (Google, Cloudflare, Microsoft, etc.)
- **Classification**: Malicious, benign, or unknown
### Why this matters for security
When you see suspicious traffic in your logs:
| GreyNoise Result | Interpretation |
|------------------|----------------|
| **NOISE + Malicious** | Background attack traffic (scanners, botnets) — likely untargeted |
| **NOISE + Benign** | Security researchers, search crawlers — usually safe |
| **RIOT** | Known good service (CDN, DNS, cloud) — almost certainly benign |
| **NOT NOISE** | ⚠️ This IP is NOT mass-scanning — traffic may be **targeted at you** |
The "NOT NOISE" case is often the most important — it suggests someone is specifically interested in your systems.
## Demo
<!-- TODO: Add GIF of Claude Desktop calling check_ip -->
**Example output from `check_ip`:**
```
IP: 51.91.185.74
Classification: MALICIOUS
Noise: YES - This IP has been observed scanning the internet
RIOT: NO - Not a known benign service IP
Last Seen: 2024-01-15
Details: https://viz.greynoise.io/ip/51.91.185.74
--- Interpretation ---
🚨 This IP is actively scanning the internet and classified as MALICIOUS.
Likely a scanner, botnet, or threat actor.
```
## Installation
### npm (recommended)
```bash
npm install -g mcp-greynoise
```
### npx (no install)
```bash
npx mcp-greynoise
```
### From source
```bash
git clone https://github.com/nickjlucker/mcp-greynoise.git
cd mcp-greynoise
npm install
npm run build
node build/index.js
```
## Configuration
### Claude Desktop
Add to your `claude_desktop_config.json`:
**macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`
**Windows:** `%APPDATA%\Claude\claude_desktop_config.json`
```json
{
"mcpServers": {
"greynoise": {
"command": "npx",
"args": ["mcp-greynoise"],
"env": {
"GREYNOISE_API_KEY": "your-api-key-here"
}
}
}
}
```
### Environment Variables
| Variable | Required | Description |
|----------|----------|-------------|
| `GREYNOISE_API_KEY` | No | API key for higher rate limits (50/day vs 10/day) |
Get a free API key at [viz.greynoise.io/signup](https://viz.greynoise.io/signup).
> ⚠️ **Never commit API keys.** See `.env.example` for the recommended setup.
## Tools
### `check_ip`
Check a single IP address against GreyNoise.
**Input:**
- `ip` (string): IPv4 address to check
### `check_ips`
Check multiple IP addresses in one call (max 10).
**Input:**
- `ips` (string[]): Array of IPv4 addresses
**Example output:**
```
=== Results ===
8.8.8.8: RIOT (benign service) [Google]
51.91.185.74: NOISE - MALICIOUS
192.168.1.1: NOT NOISE (potentially targeted)
--- Legend ---
RIOT: Known benign service (CDN, DNS, etc.)
NOISE: IP is mass-scanning the internet
NOT NOISE: IP is NOT mass-scanning (traffic may be targeted)
```
## Resources
### `greynoise://status`
Returns API status and rate limit information.
## Rate Limits
| Tier | Daily Lookups |
|------|---------------|
| Unauthenticated | 10 |
| Free account | 50 |
| Paid plans | Higher |
Rate limits are shared between API calls and the [GreyNoise Visualizer](https://viz.greynoise.io).
## Security
This server:
- **Only reads** from the GreyNoise API (no scanning, no exploitation)
- **Does not store** any data beyond the current request
- **Does not transmit** your API key anywhere except to GreyNoise
- Performs **reputation/telemetry enrichment only**
Your API key is passed via environment variable and never logged.
## Use Cases
- **SOC Triage**: Quickly determine if alert IPs are background noise or targeted
- **Incident Response**: Identify if attacker IPs are mass-scanners or focused threats
- **Threat Hunting**: Find IPs in your logs that aren't mass-scanners (potentially targeted)
- **Log Analysis**: Reduce false positives by filtering out known scanners
## Development
```bash
# Install dependencies
npm install
# Run in development mode
npm run dev
# Build for production
npm run build
# Run built version
npm start
```
## License
MIT
## Links
- [GreyNoise](https://greynoise.io)
- [GreyNoise API Docs](https://docs.greynoise.io)
- [Model Context Protocol](https://modelcontextprotocol.io)
- [MCP Registry](https://registry.modelcontextprotocol.io)
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one checks a single IP address, the other checks multiple IPs in bulk. An agent can easily distinguish between them based on the singular/plural naming and the explicit descriptions.
Both tools follow the consistent pattern of 'check_' followed by a noun indicating the input type ('ip' vs 'ips'). The naming is predictable and uses consistent snake_case throughout.
With only two tools, the server feels minimal for its domain. While both tools are necessary and well-scoped, a more comprehensive IP intelligence server would typically benefit from additional tools (e.g., contextual enrichment, history). The count is borderline thin.
The tool set covers the basic use case of checking IPs against GreyNoise data, both individually and in bulk. However, it lacks other common operations like fetching detailed threat context, searching by tags or queries, or retrieving known-good RIOT entries specifically. Notable gaps exist for a more complete threat intelligence surface.