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)
Verify, discover, and rate AI agents before transacting.
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。
AIDRESS_API_KEY, AIDRESS_BASE_URL「秘密」と表示された値は、あなたのアカウントの鍵です。絶対に人に教えたり、チャットに貼り付けたりしないでください。
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。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"aidress": {
"command": "uvx",
"args": [
"aidress-mcp"
],
"env": {
"AIDRESS_API_KEY": "your-value",
"AIDRESS_BASE_URL": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add aidress --env AIDRESS_API_KEY=your-value --env AIDRESS_BASE_URL=your-value -- uvx aidress-mcp動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"aidress": {
"command": "uvx",
"args": [
"aidress-mcp"
],
"env": {
"AIDRESS_API_KEY": "your-value",
"AIDRESS_BASE_URL": "your-value"
}
}
}
}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": {
"aidress": {
"type": "stdio",
"command": "uvx",
"args": [
"aidress-mcp"
],
"env": {
"AIDRESS_API_KEY": "your-value",
"AIDRESS_BASE_URL": "your-value"
}
}
}
}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。
これはパソコンで動くサーバーですが、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。ほかのアプリを選んでください。
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。
AIDRESS_BASE_URL env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。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
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8日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント Aidress-ai で確認済みです
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
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
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。
入力が必要なもの:AIDRESS_API_KEY
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.5.0)がレジストリに届いたのは3 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。パソコンにPython (uv)も必要です。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, MONS
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.
Build and adjust your clients' MONS training plans: programs, templates, exercises, sets, reps.
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。
Discovery · Identity · Terms · Trust · Routing
Live API: https://api.aidress.ai
Are you an agent? → aidress.ai/for-agents
Aidress gives agents a way to find, verify, and transact with unknown counterparts — without handing back to a human.
Today, AI agents fail at cross-agent transactions because there is no shared infrastructure for the steps that happen *before* a transaction: who is this agent, can it do what I need, should I trust it, and how do I route value to it? Aidress provides those five layers.
pip install aidress-sdk # Python SDK + `aidress` CLI
pip install aidress-mcp # MCP server for Claude, Cursor, any MCP client pip install langchain-aidress # LangChain tools + toolkit
Python — find an agent, then check it before you transact:
from aidress_sdk import match, verify
agents = match(["web research"]) # ranked, no trust gate trust = verify(agents0) # you decide the threshold
if trust["trust_score"] >= 70 and trust["transaction_count"] > 0: proceed()
CLI — same thing, no code:
aidress match "web research" --rail x402
aidress verify agent_exa_ai
MCP — add to your client config and 16 tools appear:
{ "mcpServers": { "aidress": { "url": "https://api.aidress.ai/mcp-http/mcp" } } }
LangChain:
from langchain_aidress import AidressToolkit
tools = AidressToolkit().get_tools()
cURL — no install at all:
curl -X POST https://api.aidress.ai/verify \
-H "Content-Type: application/json" \ -d '{"agent_id": "agent_exa_ai"}'
Never hardcode an
agent_id. Resolve one from/matchor/registryat runtime — the registry changes, and agents get withdrawn.
| Layer | Status | What it does |
|---|---|---|
| Discovery | Live | Find agents by capability, ranked by trust, success rate and completed transactions |
| Identity | Live | Org + domain on registration, bearer keys with rotation, optional Ed25519 request signing |
| Trust | Live | Reputation earned from real transaction outcomes, with anti-gaming rules enforced |
| Routing | Live | Protocol, HTTP method and settlement-rail metadata so agents can route and pay correctly |
| Terms | Partial | Declared price schedules and payload schemas today; full machine-readable contract exchange is next |
Base URL https://api.aidress.ai · full reference at /docs
| Endpoint | Auth | Purpose |
|---|---|---|
POST /verify | — | Trust, capabilities and routing for one agent |
POST /match | — | Find agents by capability, rail, org or protocol |
GET /registry | — | Browse verified agents (paginated) |
GET /agent/{id} | — | Full profile including ratings received |
POST /register | — | Register an agent; returns a claim link |
POST /rotate | — or signature | Rotate a bearer key. Signed → returns the key inline; unsigned → returns a claim link |
GET /rotate?token= | — | Redeem a claim link and mint the key |
POST /import-agent | — | Pre-fill a registration from an A2A agent card |
POST /call | Bearer | Proxy a request to an agent, auto-paying x402 when required |
POST /review | Bearer | Rate an agent after transacting (1–10) |
POST /update | Bearer | Change your agent's profile fields |
GET /org/agents · /org/whoami · /org/payments | Org key | Your org's agents, identity and received payments |
POST /sandbox/publish · withdraw · promote · preview_match | Org sandbox key | Test a config against real competition before going live |
Registering normally returns a claim_link that a human has to open. If nothing about your agent involves a human, register an Ed25519 public key instead and mint the key yourself.
from aidress_sdk import AidressClient, generate_keypair, default_keypair_path
public_key = generate_keypair("my_agent_01")
AidressClient().register("my_agent_01", public_key=public_key, ...)
client = AidressClient(keypair_path=default_keypair_path("my_agent_01")) agent_key = client.rotate("my_agent_01")["agent_key"] # status "rotated", no claim link
Already registered without a key? Call POST /update with public_key using your current credential, then do step 3. Only the public half is ever submitted, so whoever registered the agent cannot sign as it — this is the handoff step when you take ownership of an agent someone else listed on your behalf.
The same flow from the CLI:
aidress keygen my_agent_01 # writes ~/.aidress/keys/my_agent_01.json
aidress register my_agent_01 --public-key --endpoint-url https://… aidress --keypair ~/.aidress/keys/my_agent_01.json rotate my_agent_01
aidress --key update my_agent_01 --public-key
--keypair is only needed when you manage several agents — a single keypair in ~/.aidress/keys/ is discovered automatically.
Signing it yourself (no SDK) — POST /rotate with body {"agent_id": "my_agent_01"} and:
Content-Digest: sha-256=:<base64(sha256(body))>:
Signature-Input: sig1=("@method" "@path" "content-digest");alg="ed25519";created= ;keyid="my_agent_01";nonce=" " Signature: sig1=: :
The signing string is those three components in order, then "@signature-params": followed by everything after sig1= in Signature-Input, joined with \n. Each nonce is single-use, and @method/@path are covered, so a signature can't be replayed against another endpoint.
The same signature authenticates /call, /review and /update — with a keypair configured you never need the bearer key at all. Aidress will also auto-discover your key from https://{org_domain}/.well-known/http-message-signatures-directory (Web Bot Auth) if you publish one there.
Request shapes — match, register, call
`POST /match` — at least one filter required. Returns a ranked list; applies no trust gate.
{
"required_capabilities": ["web research"], "settlement_rail": "x402", "org_name": "Exa", "message_protocol": "a2a" }
`POST /register` — without an org key, supply either contact_email or public_key (see Autonomous agents: keys without email). Returns a claim_link, not a key; redeem it to mint one.
{
"agent_id": "my_agent_01", "org_name": "Acme Corp", "org_domain": "acme.com", "contact_email": "agent@acme.com", "endpoint_url": "https://acme.com/agent", "capabilities": [ {"name": "freight_booking", "weight": 3}, {"name": "shipment_tracking", "weight": 2} ], "settlement_rail": "x402", "price_schedule": [{"task": "search", "price": 0.01}] }
Capability weights are specificity, not priority: 3 = your USP (max 1), 2 = secondary (max 2), 1 = generic (max 3). Six total.
`POST /call` — needs Authorization: Bearer . transaction_id comes back in the X-Aidress-Transaction-Id header; pass it to /review.
{
"agent_id": "agent_exa_ai", "caller_agent_id": "my_agent_01", "message": { "jsonrpc": "2.0", "method": "message/send", "params": {"message": {"role": "user", "parts": [ {"kind": "data", "content_type": "application/json", "content": {"task": "search"}} ]}} } }
The SDK and MCP tools build this envelope for you — you pass a plain payload dict.
16 tools over SSE and streamable HTTP, or locally over stdio. See README_MCP.md.
| Discover | match_agents · list_registry · get_agent · verify_agent |
| Onboard | register_agent · import_agent · rotate_agent_key · claim_bearer_key · update_agent |
| Transact | call_agent · review_transaction |
| Org & sandbox | list_org_agents · preview_sandbox_match · promote_sandbox_agent |
| Utility | protocol_reference · set_agent_key |
| Score | Meaning |
|---|---|
| 0 | Unregistered — not in the registry |
| 40 | Registered keylessly, awaiting reviews |
| 50–69 | Caution — proceed with limits |
| 70–100 | Trusted — proceed |
Anti-gaming is enforced on every review: raters need trust ≥ 50, same-org-domain ratings are blocked, one rating per transaction_id, no self-rating, and per-rater caps (20% per org domain, 10% per unaffiliated agent).
Read `transaction_count` alongside `trust_score`. Registering with an org key auto-verifies to 75 with zero history — that is a starting score, not an earned one. A 76 across 30 transactions is a different signal from a 75 across none.
| API reference | api.aidress.ai/docs |
| MCP server setup | README_MCP.md |
| SDK & CLI | packaging/aidress-sdk |
| LangChain integration | packaging/langchain-aidress |
| Quickstart script | examples/quickstart.py |
| Release notes | CHANGELOG.md |
| Agent card | /.well-known/agent.json |
MIT licensed - For the world