Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
제작자가 쓴 설명(영어 원문)
Sovereign MCP Gateway — 64 governed tools with Merkle transparency log. EU AI Act ready.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
웹, 데스크톱, 모바일의 Claude에서 쓸 수 있어요:
https://mcp.obligationsign.com/mcp터미널에서 이 명령어를 실행하세요
claude mcp add --transport http agts https://mcp.obligationsign.com/mcp프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"agts": {
"url": "https://mcp.obligationsign.com/mcp"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"agts": {
"type": "http",
"url": "https://mcp.obligationsign.com/mcp"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요:
https://mcp.obligationsign.com/mcp메뉴 이름은 요금제나 시기에 따라 조금 다를 수 있어요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
아직 이 서버의 도구 목록을 읽지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 7일 점검
레지스트리 이름이 도메인 mcp.obligationsign.com 기준으로 확인되었어요(레지스트리가 도메인 소유를 확인해요)
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 점검하지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요
아직 점검하지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요
아직 점검하지 않았어요. 엔드포인트를 점검할 때 도구 목록을 읽어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 1개 중 1개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.
제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(1.0.2)은 7개월 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.
같은 카테고리에는: Spec Driven Development, Remote Desktop Commander, Agent Data Tools: Utilities
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
103 tools: JSON repair, CSV, hashes, cron, dates, units, validators. 25 free calls.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
Sovereign MCP Gateway — Governed Tool Invocation for Autonomous Agents
Model Context Protocol server that turns tool calls into cryptographically authorized, verifiable actions. 115+ governed tools across 6 layers — hybrid Ed25519 + SLH-DSA signed and Merkle-anchored. Designed to support EU AI Act, GDPR, SOC 2, ISO 27001, DORA, NIS2, and FINRA compliance.
https://mcp.obligationsign.com/mcp
| Transport | URL | Status |
|---|---|---|
| Streamable HTTP (primary) | https://mcp.obligationsign.com/mcp | Active |
| SSE (deprecated) | https://mcp.obligationsign.com/mcp/sse | Deprecated |
The gateway requires a Bearer token issued through the ObligationSign platform. All requests must include an Authorization header.
To obtain a token, register at obligationsign.com/start/.
Add to your MCP configuration:
{
"mcpServers": { "agts": { "url": "https://mcp.obligationsign.com/mcp", "headers": { "Authorization": "Bearer YOUR_TOKEN" } } } }
curl -X POST https://mcp.obligationsign.com/mcp \
-H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_TOKEN" \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {} }'
AGTS (Autonomous Governance Transparency Standard) is a transparency-backed governance protocol that converts validated machine decisions into append-only cryptographic records, independently verified by a network of witnesses and monitors.
decision → record → immutable history → verifiable truth
Every tool call passes through a five-gate firewall (Statistical, Causal, Regression, Evidence, Human-Compatible Explanation) before execution. Admitted actions are Merkle-anchored into an append-only transparency log and signed with hybrid post-quantum cryptography.
Every governance envelope produced by this server is signed with a hybrid post-quantum signature: classical Ed25519 in parallel with SLH-DSA-SHAKE-128f. The signature is verifiable today with Ed25519-only tooling and remains forgery-resistant against future quantum adversaries via SLH-DSA. Sovereign Mail additionally uses ML-KEM-512 for encrypted key exchange, and peer-trust ceremonies use ML-DSA-44.
Admit decisions for governed tool calls require an independent 3-of-4 validator quorum with constraint regulator_count ≥ 1 and auditor_count ≥ 1. Validators are deployed as separate Cloudflare Workers (agts-validator-{a,b,c,d}) with distinct ECDSA P-256 keypairs; each validator independently re-evaluates the proof bundle and signs an AGTS_VOTE_V1 certificate. The quorum certificate is then anchored alongside the governance envelope in the Merkle transparency log, so any external party can reconstruct the four signed votes and verify that quorum was honestly met.
| Tool | Description |
|---|---|
create_tunnel | Establish an attested VPN tunnel (WireGuard/IPSec/TLS) |
tunnel_status | Monitor uptime, transfer bytes, and attestation status |
disconnect_tunnel | Terminate session and log the event |
dns_query | Secure DNS resolution through the Sovereign resolver |
| Tool | Description |
|---|---|
system_health | Probe all mesh workers for status and latency |
check_alerts | Fetch the monitor alert timeline |
subscribe_alerts | Webhook subscription for real-time alerts |
check_equivocations | Fetch conflicting Signed Tree Head proofs |
gossip_status | Current state of gossip protocol and monitor identity |
| Tool | Description |
|---|---|
send_sovereign_mail | Send encrypted (internal) or plaintext (external) messages |
list_inbox | List message metadata from an inbox |
read_message | Retrieve full message content by ID |
lookup_recipient_keys | Retrieve public keys (ECDH P-384 / ML-KEM-512) |
| Tool | Description |
|---|---|
upload_file | Client-side encrypted upload with integrity anchoring |
list_files | List file metadata, sizes, and sharing status |
download_file | Retrieve ciphertext for client-side decryption |
share_file | Share files using ECDH key wrapping |
delete_file | Remove a file and create a death leaf in the log |
| Tool | Description |
|---|---|
register_claw | Create a cryptographic Claw Passport and identity keys |
scan_skill | Scan agent skills through the five-gate firewall |
claw_status | Return trust score, governance history, and quota |
export_passport | Secure export of the identity envelope |
govern_skill_exec | High-level gate for skill execution |
report_skill_execution | Link skill results to authorization |
verify_skill_proof | Cryptographic verification of skill scans |
| Tool | Description |
|---|---|
authenticate_peer | Hybrid PQC (ML-DSA-44) + Classical (ECDSA) auth ceremony |
verify_agent_identity | Fingerprint and revocation check via key registry |
exchange_credentials | Secure transport using hybrid ECDH + ML-KEM-512 |
peer_trust_network | List known peers and mutual trust status |
| Tool | Description |
|---|---|
submit_governance | Pre-execution gate evaluation (ADMIT/QUARANTINE/REFUSE) |
verify_commitment | Verify commitment in transparency log with Merkle proofs |
report_execution | Log outcome of an authorized action |
update_policy | Update firewall parameters |
list_policies | List active governance thresholds and history |
governance_report | Aggregated decision reporting |
governance_stats | Per-gate pass/fail statistics and HCE distribution |
gate_analysis | Detailed breakdown of a specific evaluation decision |
| Tool | Description |
|---|---|
memory_store | Store hierarchical key-value entries |
memory_recall | Retrieve specific entries by path |
memory_list | Prefix-based listing of memories |
memory_search | Semantic similarity search using vector embeddings |
cross_session_recall | Semantic search across historical sessions |
memory_context | Mode-based contextual summary |
consolidate_memory | Compare and compact redundant entries |
memory_gc | Garbage collection of stale entries |
set_memory_ttl | Configure automatic expiration for entries |
memory_delete | Remove specific memory paths |
| Tool | Description |
|---|---|
provision_resource | Create a billing project for an agent |
manage_spending | Freeze/unfreeze spending |
check_project_billing | Detailed usage and charge breakdown |
verify_provision | Check billing project linkage |
set_budget_alert | Configure spending thresholds |
check_budget | Real-time spend vs. cap tracking |
| Tool | Description |
|---|---|
spawn_sub_agent | Launch an isolated asynchronous sub-agent |
sub_agent_status | Poll sub-agent execution status |
sub_agent_result | Retrieve sub-agent results |
chain_delegation | Recursive delegation with budget decay and depth limits |
create_template | Define a reusable multi-step workflow |
apply_template | Instantiate a template into a running task |
list_sub_agents | List active sub-agents |
list_templates | List available workflow templates |
cancel_sub_agent | Terminate a running sub-agent |
merge_sub_results | Aggregate results from parallel sub-agents |
delegation_tree | Reconstruct the full lineage of a delegated chain |
In addition to MCP, the gateway exposes REST endpoints:
| Endpoint | Description |
|---|---|
GET /api/v1/health | Upstream service health checks |
GET /api/v1/audit | Audit log queries |
GET /api/v1/assets | Asset management |
GET /verify?commitment={hash} | Commitment verification with Merkle proof |
The MCP server is one access surface to the AGTS protocol. The full clearinghouse specification is published separately.
Agent ─── MCP Gateway ─── Five-Gate Firewall ─── Transparency Log
│ │ ├── Mail Worker (E2EE) ├── Merkle Tree ├── Drive Worker (Encrypted Storage) ├── Signed Tree Heads ├── OpenClaw (Identity) └── Gossip Protocol ├── Tunnel Worker (VPN) ├── Monitor Worker (Health) └── Protocol Worker (Governance)
Most MCP servers in the ecosystem (~83%) are thin API wrappers — a single connector exposed as one or two tools, running locally via stdio, with no authentication or validation. The production-tier servers from vendors like GitHub, Slack, and AWS (~2%) are well-built but architecturally simple: they translate tools/call into API requests for their own service.
This server operates at a different level. It is not a wrapper around an external API — it implements a full governance protocol where:
The result is that every tool call produces independently verifiable cryptographic evidence of what was authorized, what was executed, and whether the outcome matched the authorization — the kind of audit trail required in regulated industries (financial services, healthcare, legal, critical infrastructure).
The gateway's architecture is designed to support compliance across multiple regulatory frameworks. The table below maps specific requirements to the AGTS features that address them.
| Requirement | AGTS Implementation |
|---|---|
| Art. 9 — Risk management | Five-gate firewall evaluates every action before execution; QUARANTINE decisions enable human intervention |
| Art. 12 — Record-keeping | Append-only Merkle transparency log with signed governance envelopes; automatic recording of every authorization and execution event |
| Art. 13 — Transparency | Every commitment is independently verifiable with cryptographic inclusion proofs; governance decisions are explainable via the HCE (Human-Compatible Explanation) gate |
| Art. 14 — Human oversight | Gate thresholds are configurable; QUARANTINE/REFUSE decisions halt execution; policy updates are themselves governed and logged |
| Trust Principle | AGTS Implementation |
|---|---|
| Security | Hybrid Ed25519 + SLH-DSA signing; post-quantum key exchange (ML-KEM-512); Cloudflare Access authentication with email binding; per-tool rate limiting |
| Availability | Multi-worker mesh architecture with independent health monitoring; gossip protocol detects node failures; system_health probes all upstream services |
| Processing Integrity | Five-gate firewall validates every action before execution; execution outcomes are traced back to authorization; variance dete
앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요