# io.github.Jam0k/threatcluster (npm · threatcluster-mcp)

Live threat intel for agents: incidents, actors, CVEs with KEV/EPSS, ransomware leak-site victims.

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-28

## Components

- remote · `threatcluster.io`: 36/100, [markdown](https://verifymcp.io/servers/jam0k-threatcluster/threatcluster.md), [page](https://verifymcp.io/servers/jam0k-threatcluster/threatcluster)
- npm · `threatcluster-mcp`: 70/100 (this document), [markdown](https://verifymcp.io/servers/jam0k-threatcluster/threatcluster-mcp.md), [page](https://verifymcp.io/servers/jam0k-threatcluster/threatcluster-mcp)

## Channel facts

- Registry: `npm`
- Package: `threatcluster-mcp`
- Version: `0.2.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-28.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 92 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (GPL-3.0-or-later).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1760 tokens (~176/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 92/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 77% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.Jam0k/threatcluster MCP server?

io.github.Jam0k/threatcluster runs locally as an npm package, launched with npx -y threatcluster-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add jam0k-threatcluster -- npx -y threatcluster-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "jam0k-threatcluster": {
      "command": "npx",
      "args": [
        "-y",
        "threatcluster-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "jam0k-threatcluster": {
      "command": "npx",
      "args": [
        "-y",
        "threatcluster-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add jam0k-threatcluster -- npx -y threatcluster-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jam0k-threatcluster": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "threatcluster-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jam0k-threatcluster --command npx --arg -y --arg threatcluster-mcp
```

### Hermes

```yaml
mcp_servers:
  jam0k-threatcluster:
    command: "npx"
    args: ["-y", "threatcluster-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "jam0k-threatcluster": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "threatcluster-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add jam0k-threatcluster -t stdio -c npx -a -y threatcluster-mcp
```

### Other

```json
{
  "mcpServers": {
    "jam0k-threatcluster": {
      "command": "npx",
      "args": [
        "-y",
        "threatcluster-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-28 (score 70, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-26 (score 70)

First indexed and scored.

## MCP tools (10)

### `search_threats` (~231 tokens)

Search incident clusters

Keyword search over incident clusters (each cluster is one deduplicated story built from every source that covered it). Best for named things: actors, malware, vendors, products, CVE ids, companies, countries. Matching is literal: it tries the exact phrase, then all words together, then any word, and finally widens the time window if still under 3 hits; `matched_stage` says which stage matched. Use `alternatives` for spellings and synonyms (UK / United Kingdom / British). Costs 1 credit per term searched; at most 8 API calls per invocation, and `api_calls` in the result says how many were made. For one call that also covers entity profiles and the dark web use search_everything instead (5 credits).

Input parameters:

- `alternatives` (array): other names for the same thing, OR'd with query
- `days` (integer): only clusters with reporting in the last N days (free keys: up to 7)
- `limit` (integer)
- `query` (string, required): 2-4 specific words; not a sentence

### `search_everything` (~208 tokens)

Search clusters, entities and the dark web

One call across the whole corpus: incident clusters, entity profiles (actors, malware, vendors, CVEs) and dark-web ransomware listings that match the query. Costs 5 credits for the phrase; if that returns little it retries one call per word (up to 4 more, so 25 at worst) and `matched_stage` says which stage the results came from. Prefer search_threats (1 credit per term) when you only need clusters; use this when you do not know whether the name is an actor, a victim or a product, or when you want the dark-web hits too.

Input parameters:

- `days` (integer): only results with activity in the last N days (free keys: up to 7)
- `limit` (integer): max clusters (entities and dark-web hits are capped the same way)
- `query` (string, required): what to look up, e.g. 'LockBit', 'CVE-2026-83549', 'Ivanti'

### `newest_threats` (~115 tokens)

Newest incident clusters

The newest incident clusters in a window, no keyword. Use for 'what happened today / this week', 'what's new', 'what should a SOC know'. `sort_by=new` lists by first report time; `sort_by=trending` ranks by how fast coverage is growing. 1 credit.

Input parameters:

- `limit` (integer)
- `sort_by` (string)
- `time_filter` (string): window; 30d needs a paid key (free keys are clamped to 7d)

### `get_threat` (~153 tokens)

Full record for one cluster

Full record for one cluster returned by another tool: summary, timeline, the underlying articles with their source URLs, extracted entities and CVEs. Call this for the 1-3 clusters that matter before answering in depth. `identifier` is the cluster id, its 8-character short id, or the slug from a threatcluster.io/cluster/... URL. Set `include_iocs` to also fetch the cluster's validated indicators (+1 credit). 1 credit (2 with IOCs).

Input parameters:

- `identifier` (string, required): cluster id, 8-char short id, or slug
- `include_iocs` (boolean): also return validated IOCs (domains, IPs, hashes, URLs) for the cluster

### `leak_site_victims` (~228 tokens)

Ransomware leak-site victims

Ransomware leak-site victim listings: who a group claims to have hit, when, sector, country. These are claims by the groups, not confirmed breaches. Returns the newest listings matching the filters plus a tally of every listing in the window by group, sector and country, so 'most active group' and 'most hit sector' questions are answered from the tally, not the sample. Use for any question about ransomware victims, a group's activity, or a sector / country being hit. 2 credits (listings + tally).

Input parameters:

- `country` (string): ISO-2 code, e.g. US, GB
- `days` (integer): window in days (free keys: up to 7)
- `group` (string): ransomware group name, e.g. qilin, akira, lockbit5
- `limit` (integer)
- `sector` (string): e.g. Healthcare, Education, Financial Services, Manufacturing, Government
- `victim` (string): substring of a victim organisation name or domain (matched client-side over the newest listings)

### `lookup_entity` (~143 tokens)

Entity profile

Profile of a threat actor, malware family, tool, company, product, country, industry or CVE as tracked in the corpus: how often it appears, first and last seen, the recent clusters and articles it appears in, and the entities it co-occurs with. Give `entity_type` when the name is ambiguous (a company that is also a malware name). 2 credits (name resolution + profile).

Input parameters:

- `entity_type` (string): optional: apt_group, ransomware_group, malware, tool, company, platform, cve, country, industry, campaign, attack_type, mitre_attack, domain, ipv4
- `name` (string, required)

### `get_vulnerability` (~75 tokens)

CVE record

One CVE record: description, CVSS, EPSS score and percentile, CISA KEV status with due date, known ransomware use, public exploit count and links, affected vendors and products, references. 1 credit.

Input parameters:

- `cve_id` (string, required): e.g. CVE-2026-83549

### `exploited_vulnerabilities` (~188 tokens)

Recently exploited CVEs

CVEs published or updated in a window, filtered to the ones that matter: in CISA KEV (`kev_only`), with a public exploit (`has_exploit`), by severity, vendor or product. Use for 'what should we patch this week' and 'is anything in our stack being exploited'. 1 credit.

Input parameters:

- `days` (integer): window in days (free keys: up to 7)
- `has_exploit` (boolean): only CVEs with a public exploit
- `kev_only` (boolean): only CVEs in CISA's Known Exploited Vulnerabilities catalogue
- `limit` (integer)
- `product` (string): CPE product, e.g. windows, ios, fortios
- `severity` (string)
- `vendor` (string): CPE vendor, e.g. microsoft, cisco, fortinet

### `trending_entities` (~141 tokens)

Trending entities

Which threat actors, ransomware crews, malware families, tools, vendors, products, CVEs, countries and industries are rising in the corpus over a window, with mention counts and the change against the previous window. Indicator types (hashes, IPs, wallets) are left out unless named in `entity_types`. 1 credit.

Input parameters:

- `entity_types` (array): restrict to these types, e.g. ["apt_group", "ransomware_group", "malware"]
- `limit` (integer): entities per type
- `time_filter` (string): window; 30d needs a paid key (free keys are clamped to 7d)

### `api_budget` (~81 tokens)

Remaining API budget

Credits and rate-limit state from the headers of the most recent API responses in this session, plus what has been spent so far. No API call is made and nothing is charged; call it to pace yourself before a burst of lookups. Free keys: 100 credits a day, 30 requests a minute, budget refills at 00:00 UTC.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/jam0k-threatcluster/threatcluster-mcp#diagnostics

## Score history

- 2026-09-28: 70
- 2026-09-27: 70
- 2026-09-26: 70

## Common questions

### What is the io.github.Jam0k/threatcluster MCP server?

io.github.Jam0k/threatcluster is an MCP server listed in the public MCP registry as io.github.Jam0k/threatcluster. Live threat intel for agents: incidents, actors, CVEs with KEV/EPSS, ransomware leak-site victims. This page covers its npm package (threatcluster-mcp).

### Is the io.github.Jam0k/threatcluster MCP server safe to use?

io.github.Jam0k/threatcluster scores 70 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 28 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.Jam0k/threatcluster MCP server expose?

io.github.Jam0k/threatcluster exposes 10 tools: search_threats, search_everything, newest_threats, get_threat, leak_site_victims, and 5 more. Their descriptions and schemas cost roughly 1,563 tokens of context every time the server is loaded.

### Is the io.github.Jam0k/threatcluster MCP server still maintained?

io.github.Jam0k/threatcluster is still listed as active in the MCP registry. We last reached this channel on 28 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.Jam0k/threatcluster MCP server under?

io.github.Jam0k/threatcluster declares the GPL-3.0-or-later licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/threatcluster-mcp
- Socket report: https://socket.dev/npm/package/threatcluster-mcp
- Repository: https://github.com/Jam0k/Threat-Intelligence-MCP
- Changelog RSS feed: https://verifymcp.io/servers/jam0k-threatcluster/threatcluster-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/jam0k-threatcluster/threatcluster-mcp.json
- HTML version of this page: https://verifymcp.io/servers/jam0k-threatcluster/threatcluster-mcp