Skip to content
MCP server

Threatcheck

Check URLs, indicators, CVEs and emails against threat intelligence before acting

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, self-hosted, API
Runs
Locally
Version
0.1.0
Listing updated
today

Similar MCP servers

About Threatcheck

Threatcheck is an open-source MCP server for security. It runs locally on your machine and is started by your AI client.

Where many security MCP servers stop at a lookup, this one adds a gate for untrusted content. check_url is the cheaper single-URL version of that gate.

check_indicator and check_indicators return a verdict, a 0-100 risk score and the blocklists citing an IP, domain, URL, file hash, email address or phone number, up to 100 at once. Email and phone lookups give a threat verdict, never personal data. CVE tools cover full detail (CVSS, EPSS, CISA KEV status), the 20 most recent entries and those with attested recent exploitation. search_indicators finds typosquats and homoglyphs of a brand, scan_email checks raw messages for phishing, and watch_domain and watch_dependencies start daily monitoring, with ack_finding to set finding status.

The package decides nothing locally: it relays calls to the hosted isMalicious endpoint, and many calls count against your monthly quota. An optional ISMALICIOUS_API_KEY is sent as a Bearer header. MIT licensed, via npm or Docker.

Install

Run in a terminal

claude mcp add threatcheck -- npx -y @reneturcios/threatcheck

Add to claude_desktop_config.json

{
  "mcpServers": {
    "threatcheck": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/threatcheck"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "threatcheck": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/threatcheck"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "threatcheck": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/threatcheck"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "threatcheck": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/threatcheck"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "threatcheck": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/threatcheck"
      ]
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (12)

Taken from the project documentation; the running server may differ.

scan_before_use
Scans untrusted content for prompt injection and checks its URLs, domains and IPs
check_url
Pre-fetch gate for one URL, domain or IP
check_indicator
Full reputation for one indicator
get_cve
One CVE in full: severity, CVSS, EPSS, KEV status and advisories
recent_cves
Most recently published CVEs, up to 20
search_indicators
Finds listed domains resembling a brand or domain
check_indicators
Reputation for up to 100 indicators in one call
scan_email
Scans one email for phishing and malware
exploited_cves
CVEs with attested exploitation in a recent window
watch_domain
Starts daily vulnerability monitoring of a public website
watch_dependencies
Starts monitoring from a lockfile or SBOM
ack_finding
Sets the status of one of your monitoring findings

What it does

Pre-use content gate
Scans untrusted content for prompt injection and risky URLs.
Indicator reputation
Risk score and citing blocklists for IPs, domains, hashes, emails and phones.
CVE intelligence
Detail, newest entries and exploited-in-the-wild lists.
Lookalike domain search
Finds typosquats, homoglyphs and other-TLD copies of a brand.
Email scanning
Checks a raw or parsed message for phishing and malware.
Daily monitoring
Watch a domain or lockfile and triage findings.

Good for

  • Screen a fetched web page before an agent acts on it
  • Check a suspicious link, hash or phone number
  • Look up CVSS, EPSS and KEV status for a CVE
  • Find lookalike domains of your brand
  • Monitor a project's dependencies for new vulnerabilities

Pricing

Open source

MIT licence; hosted lookups count against a monthly quota, plan prices not published

Threatcheck FAQ

Does it analyse things locally?

No. It relays calls to the hosted isMalicious service.

Are calls limited?

Several tools count against a monthly quota; exploited_cves also works without a key, rate-limited by IP.

How many indicators per call?

check_indicators accepts up to 100.

Does a lookup return personal data?

No. Email and phone checks return a threat verdict only.

Is Threatcheck free?

Yes. Threatcheck is open source, so you can use and self-host it for free.

How do I add Threatcheck to Claude Code?

Run this command in your terminal: claude mcp add threatcheck -- npx -y @reneturcios/threatcheck

What are the best alternatives to Threatcheck?

The closest alternatives to Threatcheck are REA, AiSOC, redamon, x64dbg-mcp-server and Agent Roast.

Where this comes from

  • Description: written from the project's README.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers