CipherHUB Cryptography Toolkit
REMOTE · TOOLS.CIPHERHUB.CLOUD · SCANNED SEP 20
Production-grade cryptography toolkit with 31 MCP tools for classical, PQC, and KMS workflows.
Available components
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. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 55 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability75
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 19092 tokens (~303/item across 63 items; 55 tools + 8 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage99
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 98% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 55 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 56 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities40
- Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28. See how to fix → Fail
How do I install the CipherHUB Cryptography Toolkit MCP server?
CipherHUB Cryptography Toolkit is a hosted endpoint at https://tools.cipherhub.cloud/cipherhub/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.
remote · tools.cipherhub.cloud
claude mcp add --transport http bowenerchen-cipherhub 'https://tools.cipherhub.cloud/cipherhub/mcp'
{
"mcpServers": {
"bowenerchen-cipherhub": {
"url": "https://tools.cipherhub.cloud/cipherhub/mcp"
}
}
} {
"servers": {
"bowenerchen-cipherhub": {
"type": "http",
"url": "https://tools.cipherhub.cloud/cipherhub/mcp"
}
}
} [mcp_servers.bowenerchen-cipherhub] url = "https://tools.cipherhub.cloud/cipherhub/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"bowenerchen-cipherhub": {
"type": "remote",
"url": "https://tools.cipherhub.cloud/cipherhub/mcp",
"enabled": true
}
}
} openclaw mcp add bowenerchen-cipherhub --url 'https://tools.cipherhub.cloud/cipherhub/mcp' --transport streamable-http
mcp_servers:
bowenerchen-cipherhub:
url: "https://tools.cipherhub.cloud/cipherhub/mcp" {
"McpServers": {
"bowenerchen-cipherhub": {
"Transport": "http",
"Url": "https://tools.cipherhub.cloud/cipherhub/mcp"
}
}
} assistant mcp add bowenerchen-cipherhub -t streamable-http -u 'https://tools.cipherhub.cloud/cipherhub/mcp'
{
"mcpServers": {
"bowenerchen-cipherhub": {
"type": "http",
"url": "https://tools.cipherhub.cloud/cipherhub/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 17 Sept 26 0
- Server version: 1.9.4 → 1.11.0 functional
- New tool “asn1_parse” functional
- New tool “der_encode” functional
- New tool “xts_cipher” functional
- “cbor_encode” reworded the description of “json_payload” cosmetic
- “cose_sign1_verify” reworded the description of “detached_payload_in_hex” cosmetic
- 14 Sept 26 0
- Schema quality: 264 → 292 ▼ functional
- New tool “cbor_decode” functional
- New tool “cbor_encode” functional
- New tool “cms_enveloped_decrypt” functional
- New tool “cms_enveloped_encrypt” functional
- New tool “cms_enveloped_parse” functional
- New tool “cms_signed_sign” functional
- New tool “cms_signed_verify” functional
- New tool “cose_sign1_parse” functional
- New tool “cose_sign1_sign” functional
- New tool “cose_sign1_verify” functional
- 9 Sept 26 0
- Tool “ecc_key_sign” rewrote its description, which is the text the model reads security
- Tool “ecc_key_verify” rewrote its description, which is the text the model reads security
- Tool “generate_sm2” rewrote its description, which is the text the model reads security
- 8 Sept 26 0
- Stability: 0.97 → pass security
- 6 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 4 Sept 26 +1
- Schema quality: 11602 → 13209 ▼ functional
- New tool “generate_sm9” functional
- New tool “sm9_decryption” functional
- New tool “sm9_encryption” functional
- New tool “sm9_extract_key” functional
- New tool “sm9_sign” functional
- New tool “sm9_verify” functional
- 3 Sept 26 0
- Schema quality: 9638 → 11602 ▼ functional
- New tool “cert_parse” functional
- New tool “cert_verify” functional
- New tool “ctr_cipher” functional
- New tool “key_derivation” functional
- “ecc_key_exchange” reworded the description of “derived_key_length” cosmetic
- “rsa_decryption” reworded the description of “password” cosmetic
- “rsa_sign” reworded the description of “password” cosmetic
- 2 Sept 26 0
- Tool “hmac_sum” rewrote its description, which is the text the model reads security
- Tool “hybrid_kex” rewrote its description, which is the text the model reads security
- Tool “rsa_encryption” rewrote its description, which is the text the model reads security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Probed https://tools.cipherhub.cloud/cipherhub/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_256_GCM_SHA384 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=cipherhub.cloud | CN=YE1,O=Let's Encrypt,C=US | 3 Sept 2026 | 2 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 65918a79305f525e65b035185bac3b16eb2 |
| SANs: *.cipherhub.cloud, cipherhub.cloud | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of tools.cipherhub.cloud. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| cloud. | present | 7041 | 13 | Verified |
| cipherhub.cloud. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| content-security-policy | default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' blob:; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob:; font-src 'self' data:; connect-src 'self' ws: wss:; |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://tools.cipherhub.cloud/cipherhub/mcp | Verified | 200 | |
| http (plaintext) | http://tools.cipherhub.cloud/cipherhub/mcp | HTTPS enforced |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
sm9_sign ~234
[sm9_ibc] [sm9_ibc] SM9 标识签名（GM/T 0044）。签名者用 KGC 派发的用户钥签名：输入 user_private_key_in_pem（SM9ExtractKey key_kind=Sign 输出）、private_key_password（用户钥口令）、data_in_hex（消息原文 hex，签名前内部先算 SM3 摘要，流式处理，仅支持原文模式）。输出：signature_in_hex / signature_in_base64（DER 编码签名，固定 104 字节）。
| Name | Type | Req | Description |
|---|---|---|---|
| data_in_hex | string | – | 数据的十六进制字符串。RAW 模式为消息原文 Hex，DIGEST 模式为哈希摘要 Hex |
| private_key_password | string | – | 私钥的加密密码（原始字符串，非编码格式），可选 |
| user_private_key_in_pem | string | – | SM9 加密用户私钥的 PEM 文本（含 BEGIN ENCRYPTED SM9 ... PRIVATE KEY 头尾，由 SM9ExtractKey 派发） |
No output schema declared.
No examples provided.
sm9_verify ~280
[sm9_ibc] [sm9_ibc] SM9 标识验签（GM/T 0044）。验签方只需主公钥与签名者标识：输入 master_public_key_in_pem（key_kind=Sign 的主公钥）、identity（签名者标识）、data_in_hex（消息原文 hex）、signature_in_hex（DER 签名，恰 104 字节 = 208 hex 字符）。verified=false 是成功响应（签名或标识不匹配），仅输入格式非法才返回错误码 'SM9 verify failed'。
| Name | Type | Req | Description |
|---|---|---|---|
| data_in_hex | string | – | 数据的十六进制字符串。RAW 模式为消息原文 Hex，DIGEST 模式为哈希摘要 Hex |
| identity | string | – | SM9 用户标识（原始字符串，如邮箱/账号，1-63 UTF-8 字节；签名/加密/解密均与该标识绑定） |
| master_public_key_in_pem | string | – | SM9 主公钥的 PEM 文本（明文形态，验签/加密侧使用；Sign/Enc 两类主密钥的公钥标签不同） |
| signature_in_hex | string | – | 签名的十六进制字符串 |
No output schema declared.
No examples provided.
stream_cipher ~385
[symmetric_cipher] AEAD 流式加解密（认证加密）。 【算法】AES256GCM（key=32B） / ChaCha20Poly1305（key=32B） / SM4GCM（key=16B）。 【参数】 - algorithm：算法名 - process_type：Encrypt 或 Decrypt - input_data_in_hex：明文或密文 Hex（1B~16MB） - key_in_hex：密钥 Hex - nonce_in_hex：随机数 Hex（固定 12 字节 = 24 hex 字符） - associated_data_in_hex：可选附加认证数据（参与 MAC 但不加密） 【输出】output_data_in_hex、output_length、output_sha256、algorithm。 【注意】加密输出包含 16 字节 auth tag；解密失败（篡改检测）会报错。
| Name | Type | Req | Description |
|---|---|---|---|
| algorithm | string | – | 密码算法名称（具体可选值因工具而异，见工具描述） |
| associated_data_in_hex | string | – | 附加认证数据的十六进制字符串（参与 MAC 计算但不加密，可选） |
| input_data_in_hex | string | – | 输入数据的十六进制字符串（加密时为明文，解密时为密文，1B~16MB） |
| key_in_hex | string | – | 密钥的十六进制字符串。长度取决于算法：AES256=64 字符(32B)，AES128/SM4=32 字符(16B) |
| nonce_in_hex | string | – | 随机数的十六进制字符串，固定 24 个 hex 字符（12 字节） |
| process_type | string | – | 操作类型，可选值：Encrypt / Decrypt |
No output schema declared.
No examples provided.
xts_cipher ~494
[other] [symmetric_cipher] AES-XTS 可调窄分组模式加解密（IEEE 1619 / NIST SP 800-38E）。algorithm 可选 AES128XTS（key 32B = 数据密钥 16B + 调组密钥 16B）或 AES256XTS（key 64B = 32B + 32B）。tweak_in_hex 为 16 字节调整值，编码数据单元编号/扇区地址，密文与数据单元位置绑定。process_type 可选 Encrypt / Decrypt（两个变换不同，须显式声明）。输入 16B ~ 16MB，无填充，密文与明文等长；非 16 倍数的尾部自动走密文窃取（ciphertext stealing）。模式特点：各数据单元独立加密，支持并行与随机访问，同一数据单元加解密自同步；同一密钥下 tweak 严禁重复使用（否则两个数据单元明文相同会直接暴露相等关系）；XTS 只提供保密性、可塑性攻击下无认证，需要防篡改时在外层叠加 AEAD 或签名。典型使用场景：BitLocker / LUKS2 / FileVault 全盘加密，AMD SEV-SNP 以 AES-256-XTS + VEK 加密 guest 内存（tweak 按物理地址派生，每页唯一），Intel TDX 内存加密同族。返回字段：output_data_in_hex、output_length、output_sha256、algorithm。
| Name | Type | Req | Description |
|---|---|---|---|
| algorithm | string | – | 密码算法名称（具体可选值因工具而异，见工具描述） |
| input_data_in_hex | string | – | 输入数据的十六进制字符串（加密时为明文，解密时为密文，1B~16MB） |
| key_in_hex | string | – | 密钥的十六进制字符串。长度取决于算法：AES256=64 字符(32B)，AES128/SM4=32 字符(16B) |
| process_type | string | – | 操作类型，可选值：Encrypt / Decrypt |
| tweak_in_hex | string | – | – |
No output schema declared.
No examples provided.
zuc_cipher ~235
[symmetric_cipher] ZUC-128 流密码（中国商密算法）。由于 ZUC 是对称流密码，加解密为同一操作，传入明文即输出密文，反之亦然。key_in_hex 固定 16 字节（32 hex 字符），iv_in_hex 固定 16 字节（32 hex 字符），input_data_in_hex 原始数据长度 1B ~ 16MB。返回字段：output_data_in_hex（输出 Hex）、output_length（字节数）。
| Name | Type | Req | Description |
|---|---|---|---|
| input_data_in_hex | string | – | 输入数据的十六进制字符串（加密时为明文，解密时为密文，1B~16MB） |
| iv_in_hex | string | – | 初始向量的十六进制字符串，固定 32 个 hex 字符（16 字节） |
| key_in_hex | string | – | 密钥的十六进制字符串。长度取决于算法：AES256=64 字符(32B)，AES128/SM4=32 字符(16B) |
No output schema declared.
No examples provided.
What is the CipherHUB Cryptography Toolkit MCP server?
CipherHUB Cryptography Toolkit is an MCP server listed in the public MCP registry as io.github.bowenerchen/cipherhub. Production-grade cryptography toolkit with 31 MCP tools for classical, PQC, and KMS workflows. This page covers its hosted endpoint (https://tools.cipherhub.cloud/cipherhub/mcp).
Is the CipherHUB Cryptography Toolkit MCP server safe to use?
CipherHUB Cryptography Toolkit 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 CipherHUB Cryptography Toolkit MCP server expose?
CipherHUB Cryptography Toolkit exposes 55 tools: hello, generate_random_data, hash_sum, hmac_sum, key_derivation, and 50 more. Their descriptions and schemas cost roughly 18,697 tokens of context every time the server is loaded.
Does the CipherHUB Cryptography Toolkit MCP server require authentication?
No. We connected to CipherHUB Cryptography Toolkit without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the CipherHUB Cryptography Toolkit MCP server still maintained?
CipherHUB Cryptography Toolkit is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.