Nullcone Threat Intelligence
Real-time threat intel for AI agents: 890K+ IOCs incl. prompt-injection & AI-skill threats
What can you do with Nullcone Threat Intelligence?
lookup_ioc(value)— check any indicator against the feedrecent_threats(limit, min_severity)— current threat picturesubmit_ioc(...)/submit_batch(...)— contribute indicatorscheck_prompt(...)— sub-millisecond prompt-injection lookupvalidate_skill(...)/scan_skill_content(...)— vet MCP tools / AI skills before loadingpoll_since(last_id)— incremental sync, no persistent connectionget_stats(),list_families(),search_by_type(...), and more
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http nullcone-threat-intelligence 'https://nullcone.ai/mcp'
{
"mcpServers": {
"nullcone-threat-intelligence": {
"type": "http",
"url": "https://nullcone.ai/mcp"
}
}
}
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Nullcone MCP Server
Real-time threat intelligence for AI agents, exposed as a Model Context Protocol server. Check IPs, domains, URLs, hashes, CVEs, prompt-injection payloads, and malicious AI-skill / MCP-tool definitions against the Nullcone network — 890K+ IOCs, free, no API key.
Backed by nullcone.ai.
Use it (hosted — nothing to install)
The server is hosted at https://nullcone.ai/mcp over streamable HTTP. Add it to any MCP client:
Claude Code
claude mcp add --transport http nullcone https://nullcone.ai/mcp
Cursor / other MCP clients — add to your MCP config:
{
"mcpServers": {
"nullcone": {
"url": "https://nullcone.ai/mcp"
}
}
}
No signup or token required. Read tools and IOC submission are open; destructive tools (e.g. revoke_ioc) are disabled on the public endpoint.
Tools
30+ tools including:
lookup_ioc(value)— check any indicator against the feedrecent_threats(limit, min_severity)— current threat picturesubmit_ioc(...)/submit_batch(...)— contribute indicatorscheck_prompt(...)— sub-millisecond prompt-injection lookupvalidate_skill(...)/scan_skill_content(...)— vet MCP tools / AI skills before loadingpoll_since(last_id)— incremental sync, no persistent connectionget_stats(),list_families(),search_by_type(...), and more
Resources: threat://stats, threat://recent, threat://families, threat://family/{name}, threat://ioc/{value}.
Prompts: analyze_ioc, triage_alert, threat_brief.
Self-host
The server is built on the public nullcone SDK.
pip install -r requirements.txt
MCP_TRANSPORT=streamable-http MCP_PORT=8001 python server.py
Or with Docker:
docker build -t nullcone-mcp .
docker run -p 8001:8001 nullcone-mcp
Set MCP_PUBLIC=1 to run an anonymous public endpoint (disables destructive tools); omit it for full local control over stdio (MCP_TRANSPORT=stdio).
License
Rising Sun License v1.0 — see LICENSE. Free for individuals and small teams.
Frequently asked questions
What is Nullcone Threat Intelligence?
Real-time threat intel for AI agents: 890K+ IOCs incl. prompt-injection & AI-skill threats
How do I install Nullcone Threat Intelligence?
It runs as a remote server. In Claude Code: claude mcp add --transport http nullcone-threat-intelligence 'https://nullcone.ai/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does Nullcone Threat Intelligence need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is Nullcone Threat Intelligence open source?
Its code is public on GitHub, but the repository does not declare a standard license.
Who maintains Nullcone Threat Intelligence?
It is published by maco144. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.