Skip to content
MCP server

isMalicious threat intelligence for AI agents

Reputation, CVE and prompt-injection checks for IPs, URLs, hashes and email

Install
Pricing
Freemium
Platforms
CLI, API
Runs
Locally or Remotely
Version
0.8.0
Listing updated
3 days ago

About isMalicious threat intelligence for AI agents

isMalicious threat intelligence for AI agents is a freemium MCP server for security. It can run locally on your machine or as a hosted remote server.

The families include instruction override, fake system prompts, tool-call forgery, exfiltration beacons, invisible Unicode, homoglyphs and encoded payloads.

The same API answers reputation questions about IPs, domains, URLs, hashes, emails and phone numbers, looks up CVEs with CVSS, EPSS and CISA KEV status, scans a whole email for phishing, and can check whether a password appears in breach dumps. For that last check the password is hashed locally and only a 5-character prefix is sent, which is why it exists only in the local npm build. Watch tools monitor a domain or a project's lockfile against new CVEs.

It runs locally through npx or remotely at api.ismalicious.com/mcp. Without a key, the local server offers bootstrap_key to mint a free key from an email address.

Install

Run in a terminal

claude mcp add --transport http mcp-server https://api.ismalicious.com/mcp

Add to Settings → Connectors → Add custom connector

https://api.ismalicious.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server": {
      "url": "https://api.ismalicious.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp-server": {
      "type": "http",
      "url": "https://api.ismalicious.com/mcp"
    }
  }
}

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

{
  "mcpServers": {
    "mcp-server": {
      "serverUrl": "https://api.ismalicious.com/mcp"
    }
  }
}

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

{
  "mcpServers": {
    "mcp-server": {
      "type": "http",
      "url": "https://api.ismalicious.com/mcp"
    }
  }
}

Configuration

  • ISMALICIOUS_API_KEYAPI key from https://ismalicious.com/app/account. Optional: without it the server starts in bootstrap mode and offers bootstrap_key.
  • ISMALICIOUS_API_SECRETAPI secret paired with the key
  • ISMALICIOUS_API_BASEAPI base URL (defaults to https://ismalicious.com/api; https://api.ismalicious.com reaches the API host directly)
  • ISMALICIOUS_TIMEOUT_MSReplaces every tool's timeout, in milliseconds (defaults: gate 15000, check_indicator 25000, CVE and exploited_cves 10000, search_indicators 20000, check_indicators 60000, check_password_exposure 10000, scan_email 20000, watch_domain 30000, watch_dependencies 45000, ack_finding 10000). ISMALICIOUS_TIMEOUT_<TOOL>_MS, e.g. ISMALICIOUS_TIMEOUT_CHECK_INDICATOR_MS, sets one tool's timeout and wins over it
  • ISMALICIOUS_WEB_BASEBase URL for bootstrap_key, a route only https://ismalicious.com/api serves (defaults to ISMALICIOUS_API_BASE, or https://ismalicious.com/api when that is api.ismalicious.com)
  • ISMALICIOUS_CACHE_TTL_SResult cache: 0 turns it off; N caps every tool's cache lifetime at N seconds (never raises one)
  • ISMALICIOUS_PREWARM0 (or false, off, no) skips the one unauthenticated GET /health sent after initialize to open the connection

Tools this server provides (13)

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

scan_before_use
Prompt-injection scan plus link reputation over untrusted content; returns block, warn or allow.
check_url
Reputation of one URL, domain or IP before fetching it.
check_indicator
Verdict for an IP, domain, URL or hash with risk score and recommended action.
get_cve
One CVE with CVSS, EPSS, CISA KEV status and references.
recent_cves
Latest CVEs, optionally by severity.
search_indicators
Searches the corpus by pattern, source or threat class.
check_indicators
Bulk check of up to 100 indicators.
check_password_exposure
Whether a password or its hash is in known breach dumps.
scan_email
Scans one email message for phishing and malware.
exploited_cves
CVEs exploited in the wild in recent days.
watch_domain
Starts vulnerability monitoring of a website.
watch_dependencies
Starts vulnerability monitoring of a project from its lockfile.
bootstrap_key
Mints a free key from an email address.

What it does

Prompt-injection gate
Scans untrusted content and returns block, warn or allow with a sanitized copy.
Indicator reputation
Risk score, citing blocklists and recommended action for IPs, domains, URLs and hashes.
CVE intelligence
CVSS, EPSS, CISA KEV status and exploitation evidence for a CVE.
Email scanning
Reads one message for phishing and malware from sender, links and attachment hashes.
Breach password check
Hashes locally and sends only a 5-character prefix; local server only.
Vulnerability watches
Monitors a domain or lockfile and matches versions against CVEs.

Good for

  • Check a fetched web page for injection before an agent acts on it
  • Triage a suspicious URL or file hash during an incident
  • Look up whether a CVE is exploited in the wild
  • Screen inbound email for phishing
  • Monitor project dependencies for new vulnerabilities

Pricing

Freemium

Free: 250 API requests/month. Pro EUR 99/month (EUR 990/year). Basic and Enterprise on the pricing page.

Prices change. Check ismalicious.com before you buy.

isMalicious threat intelligence for AI agents FAQ

Is there a free tier?

Yes. The Free plan has 250 API requests and 1,000 scans a month with no card.

Do I need a key?

Most tools do. Without one, the local server offers only bootstrap_key and exploited_cves.

What does the paid plan cost?

Pro is listed at EUR 99 a month or EUR 990 a year; Basic and Enterprise prices are not given.

Can I use it remotely?

Yes, at https://api.ismalicious.com/mcp with the key pair in an Authorization header; check_password_exposure and bootstrap_key are local only.

How many tools are there?

The site mentions 16.

Is isMalicious threat intelligence for AI agents free?

isMalicious threat intelligence for AI agents has a free plan, with paid plans for more usage or features.

How do I add isMalicious threat intelligence for AI agents to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp-server https://api.ismalicious.com/mcp

What are the best alternatives to isMalicious threat intelligence for AI agents?

The closest alternatives to isMalicious threat intelligence for AI agents are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.

Alternatives to isMalicious threat intelligence for AI agents

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Agent Roast

    MCP server

    Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools
  3. Midplane

    MCP server

    Postgres gateway for AI agents with table grants, column masking and approval for writes

    Runs locally
    • Open source
    • 5 GitHub stars
    • Databases
  4. Leash

    MCP server

    Review what your AI touched, approve risky actions and undo supported changes

    • 1 tool
    • Remote
    • Free
    • 1 GitHub star
    • Security
  5. SecureCloud

    MCP server

    SentinelOne and IT security catalog, prices, quotes and checkout links for Israel

    • 7 tools
    • Remote
    • Free
    • Security