# `software.brainiac/threat-intelligence` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://radar.anlyon.com/servers/software.brainiac/threat-intelligence
- JSON: https://radar.anlyon.com/api/v1/servers/software.brainiac/threat-intelligence
- Version: 1.0.1 (active)
- Publisher: software.brainiac (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-11-20T01:18:29.737Z

Title and description, as the publisher wrote them:

```untrusted-server-text
BRAINIAC Threat Intelligence & Public Signals
Paid Threat Intelligence & Public Signals API via x402. Unpaid tool calls return 402.
```

Scanned 2026-11-20T01:19:17.423Z over streamable-http.

**8 tools: 6 change things and 2 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 6 | ask |
| Only reads | read | 2 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged outbound.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__threat-intelligence__threat-intelligence_domain-threat-history` `mcp__threat-intelligence__threat-intelligence_exposed-service-risk-analyze` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__threat-intelligence__threat-intelligence_certificate-threat-cluster` `mcp__threat-intelligence__threat-intelligence_domain-threat-history` `mcp__threat-intelligence__threat-intelligence_exposed-service-risk-analyze` `mcp__threat-intelligence__threat-intelligence_ioc-context-enrich` `mcp__threat-intelligence__threat-intelligence_phishing-infrastructure-cluster` `mcp__threat-intelligence__threat-intelligence_public-threat-feed-aggregate` `mcp__threat-intelligence__threat-intelligence_threat-indicator-confidence-score` `mcp__threat-intelligence__threat-intelligence_typosquatting-domain-detect` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

No check matched anything in these tool definitions.


## Changes things (6)

Creates or changes something that can be changed back. Claude Code: ask.

### `threat-intelligence_certificate-threat-cluster`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Identify relationships between domains using caller-supplied certificates and optional public crt.sh data. Shared certificate attributes are linkage evidence, not confirmed abuse. Price $0.04 USDC. POST /api/v1/threat-intelligence/certificate-threat-cluster. An unpaid call returns the x402 payment terms and does not run.
```

### `threat-intelligence_ioc-context-enrich`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Enrich supplied IPs, domains, URLs, and hashes using caller context plus optional public DNS/feeds. A single weak feed hit is never classified as malicious. Price $0.04 USDC. POST /api/v1/threat-intelligence/ioc-context-enrich. An unpaid call returns the x402 payment terms and does not run.
```

### `threat-intelligence_phishing-infrastructure-cluster`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Group related phishing domains and infrastructure using caller evidence and optional public phishing feeds. Clusters are relationship hypotheses, not confirmed campaigns. Price $0.04 USDC. POST /api/v1/threat-intelligence/phishing-infrastructure-cluster. An unpaid call returns the x402 payment terms and does not run.
```

### `threat-intelligence_public-threat-feed-aggregate`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Aggregate caller-supplied and verified key-free public threat feeds (CISA KEV, OpenPhish, capped PhishTank). URLhaus/ThreatFox require auth and are not queried. Feed hits are not confirmed malice. Price $0.05 USDC. POST /api/v1/threat-intelligence/public-threat-feed-aggregate. An unpaid call returns the x402 payment terms and does not run.
```

### `threat-intelligence_threat-indicator-confidence-score`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Calculate explainable confidence scores for supplied threat indicators using multi-source corroboration. Single weak signals are capped and never claimed as confirmed malice. Price $0.03 USDC. POST /api/v1/threat-intelligence/threat-indicator-confidence-score. An unpaid call returns the x402 payment terms and does not run.
```

### `threat-intelligence_typosquatting-domain-detect`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Identify domains resembling supplied brand or company domains using local string/keyboard heuristics. Resemblance alone is not confirmed phishing. Price $0.03 USDC. POST /api/v1/threat-intelligence/typosquatting-domain-detect. An unpaid call returns the x402 payment terms and does not run.
```

## Only reads (2)

Looks things up and changes nothing. Claude Code: allow.

### `threat-intelligence_domain-threat-history`

- The description's first verb is "analyze": a word for reading.
- Tag private-data: The input names a file (input.file), and the tool reads: it reads files.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Analyze publicly accessible domain history and DNS/RDAP context from caller fields and optional key-free public lookups. History attributes alone are not malice. Price $0.04 USDC. POST /api/v1/threat-intelligence/domain-threat-history. An unpaid call returns the x402 payment terms and does not run.
```

### `threat-intelligence_exposed-service-risk-analyze`

- The name "threat-intelligence_exposed-service-risk-analyze" says "analyze": a word for reading.
- Tag private-data: The input names a file (input.file), and the tool reads: it reads files.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Analyze caller-supplied external service inventory and scan results for exposure risk. Never initiates intrusive network scanning. Price $0.04 USDC. POST /api/v1/threat-intelligence/exposed-service-risk-analyze. An unpaid call returns the x402 payment terms and does not run.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `threat-intelligence`:

```json
{
  "permissions": {
    "allow": [
      "mcp__threat-intelligence__threat-intelligence_domain-threat-history",
      "mcp__threat-intelligence__threat-intelligence_exposed-service-risk-analyze"
    ],
    "ask": [
      "mcp__threat-intelligence__threat-intelligence_public-threat-feed-aggregate",
      "mcp__threat-intelligence__threat-intelligence_ioc-context-enrich",
      "mcp__threat-intelligence__threat-intelligence_certificate-threat-cluster",
      "mcp__threat-intelligence__threat-intelligence_typosquatting-domain-detect",
      "mcp__threat-intelligence__threat-intelligence_phishing-infrastructure-cluster",
      "mcp__threat-intelligence__threat-intelligence_threat-indicator-confidence-score"
    ],
    "deny": []
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__threat-intelligence__threat-intelligence_public-threat-feed-aggregate`: untrusted-input
- `mcp__threat-intelligence__threat-intelligence_ioc-context-enrich`: untrusted-input
- `mcp__threat-intelligence__threat-intelligence_domain-threat-history`: private-data, untrusted-input
- `mcp__threat-intelligence__threat-intelligence_certificate-threat-cluster`: untrusted-input
- `mcp__threat-intelligence__threat-intelligence_typosquatting-domain-detect`: untrusted-input
- `mcp__threat-intelligence__threat-intelligence_phishing-infrastructure-cluster`: untrusted-input
- `mcp__threat-intelligence__threat-intelligence_exposed-service-risk-analyze`: private-data, untrusted-input
- `mcp__threat-intelligence__threat-intelligence_threat-indicator-confidence-score`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:35:32.640Z, unchanged since 2026-11-20T19:35:32.640Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `6` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **warn** Tools that change things, listed to anyone ([unauth-remote-writes](https://radar.anlyon.com/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.

https://www.brainiac.software/mcp/threat-intelligence: tools/list returned 8 tools to an anonymous client, including threat-intelligence_public-threat-feed-aggregate (write), threat-intelligence_ioc-context-enrich (write), threat-intelligence_certificate-threat-cluster (write), threat-intelligence_typosquatting-domain-detect (write), threat-intelligence_phishing-infrastructure-cluster (write) and 1 more
```
