# PhishDestroy CTI

> PhishDestroy CTI is a free MCP server for security. Read-only phishing domain intelligence over MCP for checking and investigating suspicious. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** Web, API, CLI
- **Website:** https://phishdestroy.io/api/
- **MCP Registry name:** io.phishdestroy/cti
- **Categories:** security
- **Listing updated:** 2026-11-18

## About

PhishDestroy CTI is a remote MCP endpoint that gives AI assistants read-only access to phishing-domain intelligence. The Model Context Protocol listing describes it as a way to check domains, pull dated evidence reports and search by impersonated brand.

The endpoint runs over streamable HTTP and needs no key or sign-up, so it can be added to Claude, ChatGPT, Cursor or VS Code with a single URL. Lookups return a record status for each domain, and the site notes that a not_found result means no record exists rather than that the domain is safe. Bulk checks accept up to 25 domains per request, and message triage sends only the domain names to the service while the message itself stays in the chat.

The site describes its data as public threat intelligence released under CC-BY-4.0, with a separate route for commercial or high-volume use. It suits security analysts, fraud teams and developers who want reputation and evidence lookups inside an assistant workflow.

## Features

- **Single domain check:** Looks up a domain and returns its record status, assessment and third-party verdicts with dates.
- **Bulk domain lookup:** Checks up to 25 domains in one request, each with a record status and report link.
- **Brand search:** Finds published reports by domain prefix or impersonated brand, newest first.
- **Dated evidence reports:** Reports keep their observations with source, timestamp and method for each finding.
- **Message link triage:** Unwraps redirect and safe-link wrappers from a pasted message and lists the unique domains to check.

## Good for

- Asking an AI assistant whether a link in an email or text message is a known phishing site
- Checking a batch of suspicious domains in one request during an investigation
- Searching published reports for lookalike domains impersonating a particular brand
- Pulling dated evidence into a deep research workflow in ChatGPT

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http cti https://phishdestroy.io/api/mcp.php
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://phishdestroy.io/api/mcp.php
```

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

```json
{
  "mcpServers": {
    "cti": {
      "url": "https://phishdestroy.io/api/mcp.php"
    }
  }
}
```

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

```json
{
  "servers": {
    "cti": {
      "type": "http",
      "url": "https://phishdestroy.io/api/mcp.php"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "cti": {
      "serverUrl": "https://phishdestroy.io/api/mcp.php"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "cti": {
      "type": "http",
      "url": "https://phishdestroy.io/api/mcp.php"
    }
  }
}
```

## Tools

- `lookup_domains`: Checks up to 25 domains and returns each record status and report link.
- `get_domain_report`: Fetches the report for a listed domain.
- `analyze_message`: Unwraps links in a message and lists the unique domains found.

## FAQ

### Does the service need an API key or account?

The site says no key and no sign-up are required to add the endpoint to supported assistants.

### What does a not_found result mean?

The site states that not_found means there is no record for the domain, not that the domain is safe.

### How many domains can be checked at once?

The bulk lookup accepts up to 25 domains in one request.

### Is the message content sent to PhishDestroy during triage?

The site says the triage prompt keeps the message in the chat and that only domain names reach PhishDestroy.

### Is PhishDestroy CTI free?

Yes. PhishDestroy CTI is free to use.

### How do I add PhishDestroy CTI to Claude Code?

Run this command in your terminal: claude mcp add --transport http cti https://phishdestroy.io/api/mcp.php

### What are the best alternatives to PhishDestroy CTI?

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

## Where this comes from

- Description: written from the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.

## 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/phishdestroy-cti
