# threatcrush (remote · threatcrush.com)

Reputation + security findings (threatcrush.com)

- Trust score: 78/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `threatcrush.com`: 78/100 (this document), [markdown](https://verifymcp.io/servers/com-profullstack-threatcrush/api-mcp.md), [page](https://verifymcp.io/servers/com-profullstack-threatcrush/api-mcp)

## Channel facts

- Endpoint: `https://threatcrush.com/api/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-11-21.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2032 tokens (~101/item across 20 items; 20 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 80/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 39% 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.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the threatcrush MCP server?

threatcrush is a hosted endpoint at https://threatcrush.com/api/mcp, so there is nothing to install locally. 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 --transport http com-profullstack-threatcrush 'https://threatcrush.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-profullstack-threatcrush": {
      "url": "https://threatcrush.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-profullstack-threatcrush": {
      "type": "http",
      "url": "https://threatcrush.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-profullstack-threatcrush]
url = "https://threatcrush.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-profullstack-threatcrush": {
      "type": "remote",
      "url": "https://threatcrush.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-profullstack-threatcrush --url 'https://threatcrush.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-profullstack-threatcrush:
    url: "https://threatcrush.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-profullstack-threatcrush": {
      "Transport": "http",
      "Url": "https://threatcrush.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-profullstack-threatcrush -t streamable-http -u 'https://threatcrush.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-profullstack-threatcrush": {
      "type": "http",
      "url": "https://threatcrush.com/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-20 (score 78, 0)

- [functional] Server version: 1.0.0 → 1.0.1

### 2026-11-19 (score 78, +17)

- [security improvement] Authorization: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security improvement] TLS certificate: unverified → pass
- [security improvement] HSTS header: unverified → pass
- [security improvement] Transport: fail → pass
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Endpoint reachability: unreachable → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.23

### 2026-11-18 (score 61, −15)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-11-16 (score 76, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] Stability: 0.10 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Authorization: pass → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] HSTS header: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-11-15 (score 76, +1)

- [functional] Server version: 0.13 → 1.0.0

### 2026-11-13 (score 75, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-12 (score 74, +70)

- [security improvement] Authorization: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security improvement] TLS certificate: unverified → pass
- [security improvement] HSTS header: unverified → pass
- [security improvement] Transport: fail → pass
- [security] First check of Judged manipulation: pass
- [security] First check of Authorization: partial
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: 100
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 39

### 2026-11-11 (score 4)

First indexed and scored.

## MCP tools (20)

### `av_hash_lookup` (~133 tokens)

Look up file hashes (CrushAV)

CrushAV file reputation, no key needed: look up up to 100 SHA-256 file hashes. For each hash something is known about, returns `knownMalicious` (the source listing it as malware), `malwareName`, `trust` (0-100: how sure CIRCL hashlookup is that this is a published, known-good file from NSRL or a major OS/package repo) and a `fileName` it was seen as. Unknown hashes are omitted. Send hashes only, never file contents.

Input parameters:

- `hashes` (array, required): Lower-case hex SHA-256 hashes (max 100)

### `reputation_lookup` (~157 tokens)

Look up an IP or domain

Look up an IP address or a domain against the ThreatCrush community threat database (what every linked ThreatCrush daemon blocked). Returns `listed` (the corroboration bar: independent reporters agree), a 0-100 `score`, severity, reports, reporters, rules and country; a domain is answered from its A/AAAA addresses plus nichedb.dev's public answer (abuse.ch, SURBL). With Reputation Pro: 90 days of history, the /24 neighbourhood, the network owner (ASN) and how much of it is listed, city and the reasons behind the score. Registered servers, allowlisted addresses and anyone who logged in are never reported.

Input parameters:

- `indicator` (string, required): An IP address or a domain

### `reputation_bulk` (~56 tokens)

Look up many IPs or domains

Look up many IPs or domains at once (up to 100 with a free key, 1,000 with Reputation Pro). Results come back in request order; each counts against the daily allowance.

Input parameters:

- `indicators` (array, required)

### `redeem_credit_code` (~87 tokens)

Redeem a credit code

Redeem a ThreatCrush credit code (CR-XXXX-XXXX-XXXX-XXXX) into the signed-in account's credit balance (1 credit = $1.00). Needs the account's session token (`threatcrush login`), not a tc_agent_ key: agent keys belong to a team, not a person.

Input parameters:

- `code` (string, required): The credit code

### `list_invites` (~39 tokens)

List my invites

The signed-in account's invites: how many are left of 3, who joined, and whether the bonus credits were paid. Session token only.

### `create_invite` (~64 tokens)

Create an invite link

Create one invite link (each account has 3, single use, 30 days). When a new account joins on it and confirms its email, both get bonus credits. Session token only.

Input parameters:

- `note` (string): Who it is for (only you see it)

### `findings_list` (~151 tokens)

List findings

Your org's tracked findings from threatcrush scan, pentest and ai-scan (deduped across runs, with a triage status). Default: open + acknowledged. Session token or tc_agent_ key.

Input parameters:

- `limit` (number): Max 500, default 100
- `org_id` (string): Organization id (default: the key's org, or your first org)
- `severity` (string): Comma list of critical, high, medium, low, info
- `source` (string): Comma list of scan, pentest, ai-scan
- `status` (string): Comma list of open, acknowledged, fixed, false_positive, ignored, or all

### `findings_get` (~43 tokens)

Get a finding

One tracked finding with its details (code snippet, remediation, evidence), property and history.

Input parameters:

- `id` (string, required): Finding id
- `org_id` (string)

### `findings_triage` (~91 tokens)

Triage findings

Set the status and/or note of up to 500 findings: acknowledged, fixed, false_positive, ignored or open. fixed is reopened by a later run that still sees it; false_positive and ignored never are. Needs write.

Input parameters:

- `ids` (array, required)
- `note` (string): Why (shown everywhere the finding is)
- `org_id` (string)
- `status` (string)

### `incidents_list` (~172 tokens)

List incidents

Your org's incidents: what `threatcrush investigate --raise`, the daemon (critical detections) and people raised to humans. Filter by host and explicit since timestamp; only teams you can see. Session token or tc_agent_ key.

Input parameters:

- `host` (string): Filter incidents whose recorded host contains this value (for example dev2)
- `limit` (number): Max 500, default 100
- `org_id` (string): Organization id (default: the key's org, or your first org)
- `since` (string): Only incidents last seen at or after this timestamp; pass an explicit timezone when interpreting phrases such as last night
- `status` (string): Comma list of open, acknowledged, resolved, or all (default all)
- `team_id` (string)

### `incidents_get` (~83 tokens)

Get an incident

One incident: linked forensic evidence, recent events from the same observed source IP on its server, block history for that IP, saved AI assessment, multi-person assignees, fix and test progress, work history, recorded resolution/operator, findings, timeline, notes and who was paged.

Input parameters:

- `id` (string, required): Incident id
- `org_id` (string)

### `incidents_update` (~187 tokens)

Update an incident

Update fix work performed by your assigned agent or human: set multiple assignees, fix status, PR URL, test status and evidence, verification or blocker, and/or add a note. ThreatCrush catalogs the incident and does not execute remediation. Closing requires status fixed with passing tests and verification, or false_positive with a reason and verification, plus resolution.reason/action/verification. Needs write.

Input parameters:

- `assignee_id` (string|null)
- `assignee_ids` (array): Replace the assignee list with these active org/team member user IDs; [] clears it. An assignee receives write access to this incident. Use incidents_get to find member IDs and emails.
- `fix_work` (object)
- `id` (string, required)
- `note` (string)
- `org_id` (string)
- `resolution` (object)
- `status` (string)

### `incidents_raise` (~115 tokens)

Raise an incident (pages the team)

Raise an incident report (report_version 1: title, severity, source, dedupe_key, summary, verdict, findings, timeline, recommendations, optional team_id/server_id). The same dedupe_key while open updates it; a new incident pages the team by SMS and email once. Reports that contain anything shaped like a private key or mnemonic are refused. Needs write.

Input parameters:

- `org_id` (string)
- `report` (object, required): The report body, as POST /api/orgs/{id}/incidents takes it

### `webhooks_list` (~89 tokens)

List webhook endpoints

Your org's webhook endpoints (signed Standard Webhooks deliveries, retried for about three days) and the events ThreatCrush emits: detection.created, findings.raised, reputation.changed. Endpoints behind a Webhook alert destination follow your alert rules; the others get every event they subscribe to. Org owner/admin session token or an admin tc_agent_ key.

Input parameters:

- `org_id` (string)

### `webhooks_create` (~74 tokens)

Add a webhook endpoint

Add a webhook endpoint (public https URL). Returns the endpoint and its signing secret (whsec_…), shown once.

Input parameters:

- `description` (string)
- `events` (array): Event patterns: *, detection.created, findings.*, ... (default *)
- `org_id` (string)
- `url` (string, required)

### `webhooks_update` (~76 tokens)

Change a webhook endpoint

Change a webhook endpoint's url, events, description, or switch it on/off (on again clears its failure count).

Input parameters:

- `description` (string)
- `enabled` (boolean)
- `events` (array)
- `id` (string, required)
- `org_id` (string)
- `url` (string)

### `webhooks_delete` (~33 tokens)

Delete a webhook endpoint

Remove a webhook endpoint and its delivery log.

Input parameters:

- `id` (string, required)
- `org_id` (string)

### `webhooks_test` (~40 tokens)

Send a test webhook

Send a signed webhook.test event to one endpoint now and say how it went.

Input parameters:

- `id` (string, required)
- `org_id` (string)

### `webhooks_rotate_secret` (~45 tokens)

Rotate a webhook signing secret

Replace an endpoint's signing secret; the old one stops working at once. Returns the new secret.

Input parameters:

- `id` (string, required)
- `org_id` (string)

### `webhooks_deliveries` (~58 tokens)

List webhook deliveries

Recent webhook deliveries (status, attempts, last HTTP status/error, payload), for one endpoint or all.

Input parameters:

- `id` (string): Endpoint id (optional)
- `limit` (number)
- `org_id` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-profullstack-threatcrush/api-mcp#diagnostics

## Score history

- 2026-11-21: 78
- 2026-11-20: 78
- 2026-11-19: 78
- 2026-11-18: 61
- 2026-11-17: 76
- 2026-11-16: 76
- 2026-11-15: 76
- 2026-11-14: 75
- 2026-11-13: 75
- 2026-11-12: 74
- 2026-11-11: 4

## Common questions

### What is the threatcrush MCP server?

threatcrush is an MCP server listed in the public MCP registry as com.profullstack/threatcrush. Reputation + security findings (threatcrush.com). This page covers its hosted endpoint (https://threatcrush.com/api/mcp).

### Is the threatcrush MCP server safe to use?

threatcrush scores 78 out of 100 on VerifyMCP. 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 threatcrush MCP server expose?

threatcrush exposes 20 tools: av_hash_lookup, reputation_lookup, reputation_bulk, redeem_credit_code, list_invites, and 15 more. Their descriptions and schemas cost roughly 1,793 tokens of context every time the server is loaded.

### Does the threatcrush MCP server require authentication?

Yes. threatcrush asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the threatcrush MCP server still maintained?

threatcrush is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the threatcrush MCP server?

VerifyMCP ran 13 checks on threatcrush, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://threatcrush.com/api/mcp
- Website: https://threatcrush.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-profullstack-threatcrush/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-profullstack-threatcrush/api-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-profullstack-threatcrush/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-profullstack-threatcrush/api-mcp
