# Maskbreak

> Maskbreak is a freemium MCP server for security. MCP server for IP lookups: Tor exit and cloud-hosting signals plus API status. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** CLI, API, Web
- **Website:** https://maskbreak.com/mcp-server
- **Repository:** https://github.com/sentinelsup/maskbreak-mcp
- **MCP Registry name:** com.maskbreak/mcp
- **Categories:** security
- **Listing updated:** 2026-11-15

## About

Maskbreak is a fraud-detection API, and this server exposes its public IP intelligence to agents. It has two read-only tools. lookup_ip takes an IPv4 or IPv6 address and returns whether it is known, a verdict of allow, review or block, a risk score and nullable network details. Coverage is limited to cloud-hosting ranges and Tor exit nodes. service_status reports API health, uptime and latency.

The README is careful about limits: an unknown IP or allow verdict is not proof of safety, and it cannot tell whether an address is a VPN or proxy; that needs the REST API's live visit check with a browser script. Device fingerprinting, fake-browser detection and multi-account linking also sit outside these tools.

It runs locally through npx with a MASKBREAK_API_KEY, or as a hosted endpoint at maskbreak.com/mcp. Without a key a rate-limited free web endpoint allows 12 lookups a minute and 80 a day per caller IP. The Free plan includes 100,000 address lookups a month and paid plans start at 29 euros a month. The package is MIT licensed.

## Features

- **IP lookup:** Returns known status, verdict, risk score and network data.
- **Tor exit detection:** Flags Tor exit nodes as block.
- **Cloud-host detection:** Names the cloud provider's published range for review.
- **Service status:** Reports API health, uptime and latency.
- **Keyless mode:** Works without a key at reduced limits.
- **Hosted or local:** Run via npx or use the hosted HTTP endpoint.

## Good for

- Check a chargeback order's IP during support triage
- Classify the source of a traffic spike
- Verify a signup integration against a known Tor exit
- Check the Maskbreak API is up

## Install

### Claude Code (Terminal)

```sh
claude mcp add mcp --env MASKBREAK_API_KEY='<MASKBREAK_API_KEY>' -- npx -y @sentinelsup/mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@sentinelsup/mcp"
      ],
      "env": {
        "MASKBREAK_API_KEY": "<MASKBREAK_API_KEY>"
      }
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@sentinelsup/mcp"
      ],
      "env": {
        "MASKBREAK_API_KEY": "<MASKBREAK_API_KEY>"
      }
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@sentinelsup/mcp"
      ],
      "env": {
        "MASKBREAK_API_KEY": "<MASKBREAK_API_KEY>"
      }
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@sentinelsup/mcp"
      ],
      "env": {
        "MASKBREAK_API_KEY": "<MASKBREAK_API_KEY>"
      }
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@sentinelsup/mcp"
      ],
      "env": {
        "MASKBREAK_API_KEY": "<MASKBREAK_API_KEY>"
      }
    }
  }
}
```

## Tools

- `lookup_ip`: Looks up a public IP for Tor and cloud-hosting signals with a verdict and risk score
- `service_status`: Reports Maskbreak API health, uptime and latency

## FAQ

### Does it detect VPNs?

No. VPN and proxy verdicts need the REST API's live visit check.

### Do I need an API key?

No, but keyless use is limited to 12 lookups a minute and 80 a day per caller IP.

### What does the free plan give?

100,000 address lookups a month with an API key, no card.

### Is an allow verdict proof of safety?

No. Unknown IPs and allow verdicts are not proof of safety.

### Is Maskbreak free?

Maskbreak has a free plan, with paid plans for more usage or features.

### How do I add Maskbreak to Claude Code?

Run this command in your terminal: claude mcp add mcp --env MASKBREAK_API_KEY='<MASKBREAK_API_KEY>' -- npx -y @sentinelsup/mcp

### What are the best alternatives to Maskbreak?

The closest alternatives to Maskbreak are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Agent Roast](https://ai-powered.com/mcp/agent-roast): Agent Roast is an open-source MCP server for developer tools.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.
- [Leash](https://ai-powered.com/mcp/leash): Leash is a free MCP server for security.
- [Tinplate Edge AI Safety, Security & EU Compliance](https://ai-powered.com/mcp/tinplate-edge-ai-safety-security-and-eu-compliance): Tinplate Edge AI Safety, Security & EU Compliance is a freemium MCP server for security.
- [SecureCloud](https://ai-powered.com/mcp/securecloud): SecureCloud is a free MCP server for security.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.
- [SynomosAI Governance MCP](https://ai-powered.com/mcp/synomosai-governance-mcp-2): SynomosAI Governance MCP is an open-source MCP server for security.

---
Source: https://ai-powered.com/mcp/maskbreak
