Threat intelligence API / integrations

MCP server

Give any MCP client live threat intelligence: ten read-only tools for Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and Zed, served straight from the API at https://threatcluster.io/mcp. Incident clusters with scores and timelines, entity profiles, CVE records with KEV and exploit status, and ransomware leak-site victims, each result with the URLs to cite and the credits it cost. A free key covers all of it.

Endpointhttps://threatcluster.io/mcpSource on GitHubnpm: threatcluster-mcp

Point your client at https://threatcluster.io/mcp with your key in the X-API-Key header. There is nothing to install and nothing to keep up to date: the tools are served from the API itself, so a client only needs the URL and a key. Every call is authenticated as you, against your own credits, scopes and tier.

If your client only speaks stdio, npx -y threatcluster-mcp (Node 18+) runs the same ten tools on your machine and talks to the same REST API. Source: github.com/Jam0k/Threat-Intelligence-MCP.

Prerequisites

1. A ThreatCluster account (Free works) and an API key from Settings → API & Feeds. Free keys get 100 credits per day, 30 requests per minute, a 7-day lookback window and the five read scopes.
2. An MCP client that speaks streamable HTTP — Claude Code, Claude Desktop, Cursor, VS Code, Windsurf and Zed all do. For the stdio fallback you need Node 18+ so npx can fetch the package.

Setup: Claude Code

claude mcp add --transport http threatcluster https://threatcluster.io/mcp --header "X-API-Key: tc_live_..."

Then ask a question that needs live data, for example "an alert just came in mentioning CVE-2026-83549, what does ThreatCluster know and which clusters is it in"; Claude calls get_vulnerability and search_threats itself and cites the URLs it gets back.

Stdio fallback: claude mcp add threatcluster -e THREATCLUSTER_API_KEY=tc_live_... -- npx -y threatcluster-mcp.

Setup: Claude Desktop

Settings → Developer → Edit Config opens claude_desktop_config.json. Add the server and restart Claude Desktop:

{
  "mcpServers": {
    "threatcluster": {
      "type": "http",
      "url": "https://threatcluster.io/mcp",
      "headers": { "X-API-Key": "tc_live_..." }
    }
  }
}

Stdio fallback: replace that block with "command": "npx", "args": ["-y", "threatcluster-mcp"], "env": { "THREATCLUSTER_API_KEY": "tc_live_..." }.

Setup: Cursor

One click: install ThreatCluster in Cursor, then paste your key into the server's headers in Cursor Settings → MCP. Or add it by hand to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):

{
  "mcpServers": {
    "threatcluster": {
      "url": "https://threatcluster.io/mcp",
      "headers": { "X-API-Key": "tc_live_..." }
    }
  }
}

Setup: VS Code

Create .vscode/mcp.json in the workspace. The inputs entry makes VS Code prompt for the key and store it in its secret store rather than in the file:

{
  "inputs": [
    { "type": "promptString", "id": "tc-key", "description": "ThreatCluster API key", "password": true }
  ],
  "servers": {
    "threatcluster": {
      "type": "http",
      "url": "https://threatcluster.io/mcp",
      "headers": { "X-API-Key": "${input:tc-key}" }
    }
  }
}

Setup: Windsurf and Zed

Windsurf reads ~/.codeium/windsurf/mcp_config.json with the same mcpServers block as Claude Desktop. Zed takes a context_servers entry in settings.json:

{
  "context_servers": {
    "threatcluster": {
      "url": "https://threatcluster.io/mcp",
      "headers": { "X-API-Key": "tc_live_..." }
    }
  }
}

To check the endpoint and your key without a client:

curl -s https://threatcluster.io/mcp \
  -H "X-API-Key: tc_live_..." \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

It answers with the tool list, or 401 if the key is missing or invalid. For the stdio fallback, THREATCLUSTER_API_KEY=... npx -y threatcluster-mcp --check prints where the key came from and where it will be sent, never the key itself.

Tools and what they cost

Costs are API credits (a free key has 100 a day); an empty result or an error is refunded, so a miss costs nothing. Every result carries cost, budget (remaining today, read from the response headers) and a url on every cluster, entity, victim and CVE so the model can cite what it used.

One prompt, threatcluster_analyst, carries the analyst rules: call tools first, say what period you searched, cite every fact with the returned URL, treat leak-site listings as claims. Errors come back as tool errors with the API's own message: a 401 tells the agent to set THREATCLUSTER_API_KEY and where a free key comes from, a 429 carries the Retry-After, a 403 names the missing scope or the lookback window and the plan that lifts it.

What a result looks like

search_threats with {"query": "Cleo Harmony", "days": 7, "limit": 3}, trimmed:

{
  "tool": "search_threats",
  "as_of": "2026-09-04T16:05:34Z",
  "cost": 3,
  "budget": {
    "remaining": 97,
    "limit": 100,
    "resets_at": "2026-09-05T00:00:00Z"
  },
  "query": "Cleo Harmony",
  "matched_stage": "any word",
  "window_searched": "7d",
  "api_calls": 3,
  "count": 2,
  "clusters": [
    {
      "short_id": "2532fa3d",
      "title": "Critical Cleo Harmony Vulnerability Exploited for Privilege Escalation",
      "date": "2026-09-02",
      "threat_score": 72.9,
      "urgency": "medium",
      "summary": "A newly discovered authentication bypass vulnerability in Cleo Harmony, tracked as CVE-2026-84115, allows remote attacke…",
      "entities": {
        "ransomware_group": [
          "Cl0p"
        ],
        "cve": [
          "CVE-2026-0768",
          "CVE-2026-81578",
          "CVE-2026-82078"
        ],
        "platform": [
          "Cleo Harmony",
          "JFrog Artifactory",
          "Langflow"
        ]
      },
      "url": "https://threatcluster.io/cluster/critical-cleo-harmony-vulnerability-exploited-2532fa3d"
    },
    "…"
  ]
}

Budgets for agents

Cheap reads cost 1 credit, search_everything costs 5 and search_threats costs 1 per term it tries (it stops as soon as three clusters match, and never makes more than eight calls). api_budget costs nothing and reports what the last responses said about the day's remaining credits, so an agent can pace itself before a burst of lookups. An exhausted budget returns a 429 with Retry-After; the budget refills at 00:00 UTC.

For unattended agents, mint a scoped tc_agent_ key rather than handing over a personal key; it supports scope downgrade and per-session request caps. Details at /cli.

Security

The key leaves the process in exactly one place, the X-API-Key header: never logged, never written to disk, scrubbed from every error string. All tools are read-only.

Prefer a bare function to a server? The agent-tool script is a 60-line threatcluster_lookup(query) for OpenAI or Claude function calling. Full endpoint reference: /api/public/v1/docs. Plans and credits: /pricing.