Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者による説明(英語の原文)
Sovereign MCP Gateway — 64 governed tools with Merkle transparency log. EU AI Act ready.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
ウェブ、デスクトップ、モバイルのClaudeで使えます:
https://mcp.obligationsign.com/mcpターミナルでこれを実行します
claude mcp add --transport http agts https://mcp.obligationsign.com/mcpプロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"agts": {
"url": "https://mcp.obligationsign.com/mcp"
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"agts": {
"type": "http",
"url": "https://mcp.obligationsign.com/mcp"
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
ChatGPTがつなげるのは、インターネット上のサーバーだけです:
https://mcp.obligationsign.com/mcpメニューの名前は、プランや時期によって少し違うことがあります。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
このサーバーのツール一覧はまだ読み取っていません。エンドポイントは順番にチェックしています。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月7日にチェック
レジストリ名はドメイン mcp.obligationsign.com で確認済みです(レジストリがドメインの所有を確認しています)
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
まだチェックしていません。エンドポイントは順番にチェックしています
まだチェックしていません。エンドポイントは順番にチェックしています
まだチェックしていません。エンドポイントをチェックするときにツール一覧を読み取ります
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
作者のクラウドで動きます。インストール不要でインターネット経由でつながりますが、送った内容は作者のサーバーを通ります。
GitHubリポジトリの最終更新は–、最新バージョン(1.0.2)がレジストリに届いたのは7 か月前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。URLでつながるので、リモートMCPサーバーに対応したアプリ(開発者モードのChatGPTなど)でも使えます。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, First Sale Scout
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
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.
Playbooks and a 14-day checklist for founders winning their first paying customers.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
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
冒頭だけを表示しています。続きはリポジトリで読めます