# `com.quickcoderhub/security-crypto` 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/com.quickcoderhub/security-crypto
- JSON: https://radar.anlyon.com/api/v1/servers/com.quickcoderhub/security-crypto
- Version: 1.0.0 (active)
- Publisher: com.quickcoderhub (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/Youismw/quickcoderhub-web
- Metadata from the official MCP Registry, synced 2026-11-19T13:17:42.204Z

Title and description, as the publisher wrote them:

```untrusted-server-text
20 Security MCP tools: X.509, SAML, JWT, PGP, SSH, CSP/CORS, SBOM, lockfiles, AES/scrypt.
```

Scanned 2026-11-19T13:18:23.373Z over streamable-http.

**20 tools: 16 change things and 4 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 16 | ask |
| Only reads | read | 4 | allow |

## Exfil surface

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

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__security-crypto__pgp_packet_inspect` `mcp__security-crypto__sbom_inspect_and_audit` `mcp__security-crypto__ssh_known_hosts_inspect` `mcp__security-crypto__x509_certificate_inspect` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | none |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

- **high** References to secrets on disk in `ssh_config_generate_and_audit` ([sensitive-path](https://radar.anlyon.com/methodology#sensitive-path))

```untrusted-server-text
The description refers to "~/.ssh/config".

description: "Generate hardened ~/.ssh/config stanzas (JumpHost/ProxyJump, IdentityFi..."
```

- **high** References to secrets on disk in `ssh_config_generate_and_audit` ([sensitive-path](https://radar.anlyon.com/methodology#sensitive-path))

```untrusted-server-text
The input schema at properties.identityFile.default refers to "~/.ssh/id_ed25519".

inputSchema.properties.identityFile.default: "~/.ssh/id_ed25519"
```

- **high** References to secrets on disk in `ssh_known_hosts_inspect` ([sensitive-path](https://radar.anlyon.com/methodology#sensitive-path))

```untrusted-server-text
The description refers to "~/.ssh/known_hosts".

description: "Inspect ~/.ssh/known_hosts entries for hashed vs plaintext hostnam..."
```

- **info** The word "credentials" in `cors_preflight_simulate` ([credentials-mention](https://radar.anlyon.com/methodology#credentials-mention))

```untrusted-server-text
The description mentions "Credentials".

description: "...inst Access-Control-Allow-Origin, Allow-Credentials, and Allow-Methods rules and flag RFC m..."
```


## Changes things (16)

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

### `aes_gcm_encrypt_decrypt`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Authenticated AES-256-GCM encryption and decryption using Node crypto with random 96-bit IVs and 128-bit GCM auth tags.
```

### `bip39_entropy_mnemonic`

- The description's first verb is "generate": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Generate 128-bit or 256-bit cryptographic entropy with its exact BIP-39 SHA-256 checksum bits and 11-bit word indices.
```

### `cors_preflight_simulate`

- Nothing in its name or description says what it does, so it is counted as a write.
- Findings: info credentials-mention

Description, as the server wrote it:

```untrusted-server-text
Simulate a browser CORS preflight check against Access-Control-Allow-Origin, Allow-Credentials, and Allow-Methods rules and flag RFC misconfigurations.
```

### `crypto_keypair_generate`

- The name "crypto_keypair_generate" says "generate": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Generate fresh Ed25519 or RSA-2048/4096 PKCS#8/SPKI PEM keypairs and SHA-256 public key fingerprints via Node crypto.
```

### `csp_parse_and_audit`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Parse, build, or security-audit Content-Security-Policy (CSP) headers for unsafe-inline, unsafe-eval, wildcard sources, and missing frame-ancestors.
```

### `hmac_sign_and_verify`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Compute or timing-safe verify HMAC-SHA256 / HMAC-SHA512 message authentication codes.
```

### `ioc_defang_and_refang`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Safely defang or refang malicious IOC URLs, domains, email addresses, and IPv4 indicators (hxxp://, [.], [@]) for SOC reports.
```

### `jwt_decode_and_audit`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Decode JWT header & payload, flag alg=none / weak secrets / expired exp claims, and optionally verify HS256/HS512 signatures.
```

### `lockfile_integrity_audit`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Audit npm package-lock.json (v2/v3) for non-HTTPS registry URLs, missing SHA-512 integrity hashes, and total transitive package footprint.
```

### `package_json_audit`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Audit an npm package.json manifest for unpinned git/http dependencies, risky preinstall/postinstall lifecycle hooks, and missing engines/exports.
```

### `password_kdf_hash_and_verify`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Hash and verify passwords using cryptographic scrypt or PBKDF2-SHA512 with random 16-byte salts via Node crypto.
```

### `permissions_policy_audit`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Parse or build HTTP Permissions-Policy feature allowlists (camera, microphone, geolocation, usb, payment) and flag wildcard feature exposure.
```

### `referrer_policy_audit`

- The description's first verb is "evaluate": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Evaluate HTTP Referrer-Policy values for cross-origin query string/URL leakage risk and recommend strict alternatives.
```

### `saml_assertion_decode`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Decode Base64 / URL-encoded / Deflate SAML 2.0 AuthnRequests or Responses and extract Issuer, NameID, Audience, and validity timestamps.
```

### `spdx_license_compatibility`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Classify SPDX open-source license identifiers (MIT, Apache-2.0, BSD, GPL-3.0, AGPL-3.0) by copyleft tier, patent grant, and commercial risk.
```

### `ssh_config_generate_and_audit`

- The name "ssh_config_generate_and_audit" says "generate": a word for a change.
- Findings: high sensitive-path, high sensitive-path

Description, as the server wrote it:

```untrusted-server-text
Generate hardened ~/.ssh/config stanzas (JumpHost/ProxyJump, IdentityFile, IdentitiesOnly, ServerAliveInterval) or audit existing SSH configs.
```

## Only reads (4)

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

### `pgp_packet_inspect`

- The name "pgp_packet_inspect" says "inspect": a word for reading.
- Tag private-data: The input names a file (input.filePath), and the tool reads: it reads files.

Description, as the server wrote it:

```untrusted-server-text
Parse ASCII-armored OpenPGP public/private keys or signatures to decode RFC-4880 packet tags, RSA/EdDSA versions, CRC24 armor checksum, and User IDs.
```

### `sbom_inspect_and_audit`

- The name "sbom_inspect_and_audit" says "inspect": a word for reading.
- Tag private-data: The input names a file (input.filePath), and the tool reads: it reads files.

Description, as the server wrote it:

```untrusted-server-text
Inspect CycloneDX or SPDX JSON Software Bill of Materials (SBOM) to count components, extract PURLs, and summarize license distribution.
```

### `ssh_known_hosts_inspect`

- The name "ssh_known_hosts_inspect" says "inspect": a word for reading.
- Tag private-data: The input names a file (input.filePath), and the tool reads: it reads files.
- Findings: high sensitive-path

Description, as the server wrote it:

```untrusted-server-text
Inspect ~/.ssh/known_hosts entries for hashed vs plaintext hostnames, deprecated ssh-dss/ssh-rsa keys, and duplicate key fingerprints.
```

### `x509_certificate_inspect`

- The name "x509_certificate_inspect" says "inspect": a word for reading.
- Tag private-data: The input names a file (input.filePath), and the tool reads: it reads files.

Description, as the server wrote it:

```untrusted-server-text
Inspect an X.509 PEM/DER TLS certificate using Node crypto.X509Certificate for subject, issuer, SANs, expiry, fingerprint256, and key type.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__security-crypto__x509_certificate_inspect",
      "mcp__security-crypto__pgp_packet_inspect",
      "mcp__security-crypto__ssh_known_hosts_inspect",
      "mcp__security-crypto__sbom_inspect_and_audit"
    ],
    "ask": [
      "mcp__security-crypto__saml_assertion_decode",
      "mcp__security-crypto__jwt_decode_and_audit",
      "mcp__security-crypto__crypto_keypair_generate",
      "mcp__security-crypto__ssh_config_generate_and_audit",
      "mcp__security-crypto__csp_parse_and_audit",
      "mcp__security-crypto__cors_preflight_simulate",
      "mcp__security-crypto__permissions_policy_audit",
      "mcp__security-crypto__referrer_policy_audit",
      "mcp__security-crypto__ioc_defang_and_refang",
      "mcp__security-crypto__spdx_license_compatibility",
      "mcp__security-crypto__package_json_audit",
      "mcp__security-crypto__lockfile_integrity_audit",
      "mcp__security-crypto__password_kdf_hash_and_verify",
      "mcp__security-crypto__aes_gcm_encrypt_decrypt",
      "mcp__security-crypto__hmac_sign_and_verify",
      "mcp__security-crypto__bip39_entropy_mnemonic"
    ],
    "deny": []
  }
}
```

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

- `mcp__security-crypto__x509_certificate_inspect`: private-data
- `mcp__security-crypto__pgp_packet_inspect`: private-data
- `mcp__security-crypto__ssh_known_hosts_inspect`: private-data
- `mcp__security-crypto__sbom_inspect_and_audit`: private-data

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-19T17:25:12.322Z, unchanged since 2026-11-19T17:25:12.322Z. 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 | `16` |
| 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 16 tools that change things (16 write). Whether a call also works without credentials was not tested: tools are never called.

https://api.quickcoderhub.com/mcp/security-crypto: tools/list returned 20 tools to an anonymous client, including saml_assertion_decode (write), jwt_decode_and_audit (write), crypto_keypair_generate (write), ssh_config_generate_and_audit (write), csp_parse_and_audit (write) and 11 more
```
