Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
제작자가 쓴 설명(영어 원문)
Lets an agent pay for x402 APIs in USDC on Arc, under a spending policy it cannot change.
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.
CRA_NETWORK, CRA_KEY_FILE, CRA_POLICY, CRA_RPC_URL, DATABASE_URL필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
Claude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요
{
"mcpServers": {
"cra-agent": {
"command": "npx",
"args": [
"-y",
"@cra-agent/mcp"
],
"env": {
"CRA_NETWORK": "your-value",
"CRA_KEY_FILE": "your-value",
"CRA_POLICY": "your-value",
"CRA_RPC_URL": "your-value",
"DATABASE_URL": "your-value"
}
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add cra-agent --env CRA_NETWORK=your-value --env CRA_KEY_FILE=your-value --env CRA_POLICY=your-value --env CRA_RPC_URL=your-value --env DATABASE_URL=your-value -- npx -y @cra-agent/mcp실행하기 전에 빈 값을 채워 주세요.
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"cra-agent": {
"command": "npx",
"args": [
"-y",
"@cra-agent/mcp"
],
"env": {
"CRA_NETWORK": "your-value",
"CRA_KEY_FILE": "your-value",
"CRA_POLICY": "your-value",
"CRA_RPC_URL": "your-value",
"DATABASE_URL": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"cra-agent": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cra-agent/mcp"
],
"env": {
"CRA_NETWORK": "your-value",
"CRA_KEY_FILE": "your-value",
"CRA_POLICY": "your-value",
"CRA_RPC_URL": "your-value",
"DATABASE_URL": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
이 서버는 내 컴퓨터에서 실행되는데, ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요. 다른 앱을 고르세요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
CRA_POLICY envCRA_RPC_URL envDATABASE_URL env이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
내 컴퓨터에서 실행돼요. 설치하면 AI 앱에 도구 목록이 나타나요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 7일 점검
레지스트리 이름이 GitHub 계정 giupy997 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
내 컴퓨터에서 실행되는 서버라 인터넷 엔드포인트가 없어요
내 컴퓨터에서 실행되며, 대신 로컬 설정을 사용해요
내 컴퓨터에서 실행돼요. 도구 목록은 인터넷 엔드포인트가 있는 서버에서만 읽을 수 있어요
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.
입력해야 할 값: CRA_NETWORK, CRA_KEY_FILE
내 컴퓨터에서 실행돼요. AI 앱이 필요할 때 실행하고, 데이터는 제작자의 서버를 거치지 않아요(서버 자체가 온라인 서비스를 호출하는 경우는 제외).
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(0.0.11)은 44일 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. 내 컴퓨터에 Node.js도 있어야 해요.
같은 카테고리에는: Spec Driven Development, Remote Desktop Commander, Tools MCP
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.
Web production tools for AI agents: contrast, JP text, WebP, JSON-LD, slugs, dates and 40+ more
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
An MCP server that lets an AI agent pay for an API call. The agent calls one tool, the rail reads the x402 price, checks a spending policy, pays in USDC on Arc through Circle Gateway with no gas for the buyer, and keeps the receipt.
The model never sees the key, and it cannot raise its own limit: both are read from the environment before the conversation starts.
npm i -g @cra-agent/mcp
cra-agent init --client claude-desktop
Creates the agent's key in ~/.cra-agent/agent.key (readable only by you, never overwritten), checks the limits, writes the entry into the client's config file with a copy of the old one, and prints the address to fund. --client is claude-desktop, cursor, claude-code or terminal; --policy, --network, --key-file and --dry-run do what they say. CRA Factory writes the command for you from four questions.
{ "mcpServers": { "cra-agent": {
"command": "cra-agent-mcp", "env": { "CRA_NETWORK": "arc", "CRA_KEY_FILE": "/path/to/agent.key", "CRA_POLICY": "daily=5,per_seller=0.5,per_payment=0.05" } } } }
CRA_KEY_FILE points at a file holding the private key, chmod 600. Never put a key in a prompt.
| Tool | What it does |
|---|---|
arc_search | Finds what can be bought on Arc from a few words ("bitcoin price", "web search"): CRA AGENT's own data, the CRA market, and the endpoints Circle's x402 catalogue lists as payable on Arc (Exa, Goldsky, BlockRun and others). Each result: the method and the URL with example parameters, where each parameter goes (query, path or JSON body), the price, the seller, who listed it, and whether your policy allows paying it now. Free. |
arc_quote | Reads the price of a URL and says whether the policy would allow it. Pays nothing. For a POST, pass the body the payment will carry: some sellers check it before they name a price. |
arc_pay | Pays for the URL and returns the response with a receipt. With lightning: true it pays in bitcoin over Lightning when the seller's 402 offers it (x402 exact on lnbtc), from the wallet in CRA_NWC_PAY_FILE, under the same limits in dollars. Limits are checked on what the 402 asks at pay time, before anything is signed. maxUsdc adds a ceiling for that one call: pass the price arc_search listed, and a seller who raised it since is refused even inside your limits. |
arc_balance | Wallet and Circle Gateway balances. |
arc_deposit | Moves wallet USDC into the Gateway balance. Needed once before the first payment. |
arc_ledger | Every attempt: quoted, rejected, signed, settled, failed. |
arc_proof | Matches settled payments to the on-chain transfer that carried them. |
arc_verify_receipt | Checks a signed receipt from another agent: who signed it, and whether the payment fitted the limits it states. |
arc_policy | Shows the limits in force. |
arc_job_* | ERC-8183 escrow jobs. Testnet only until the contract is deployed on Arc mainnet. |
cra-agent think " " runs a small autonomous agent whose brain is a pay-per-call LLM on Arc: BlockRun's chat completions, found in the bazaar, Claude Haiku 4.5 by default. Every thought is a paid call, and so is every tool the brain asks for: it searches the bazaar for free, then buys what it needs at the listed price. There is no API key anywhere, only the agent's wallet. The session budget (--budget, default $0.10) and the spending policy cover thinking and tools alike, a thought is capped with --ceiling (default $0.01), and the brain can only buy a URL that one of its searches returned. It prints each step with its cost and ends with the bill: so much for thinking, so much for tools. A short task costs a few cents: the run on cra-agent.tech/think that found when Arc mainnet went live and who validates it cost $0.023648, four thoughts and one web search from Exa.
It also knows a few free public APIs, called without paying and shown as such: DexScreener's pairs, boosted tokens and new token profiles, digested to what answers questions (pairs by 24-hour volume). --tools keeps it to a list of URL prefixes: anything else is never shown to it, so never bought.
With --record and a DATABASE_URL, the run is kept in Postgres as it happens, step by step, which is how the page shows it live and replays it after. --questions picks the question when none is given, which is how our server runs it on a timer: the file combines templates (What is the price of {coin} right now?) with lists (@coin = bitcoin (BTC) | ether (ETH)), and a recorded run never repeats one of the last hundred questions.
The same agent can be hired by anyone, over x402 upto: GET https://api.cra-agent.tech/v1/upto/think?task=… asks you to sign for up to $0.10 and charges what the run spent plus $0.005. arc_pay and cra-agent pay pay routes like this one: your policy is checked against the ceiling, since all of it could be taken, and your ledger keeps what was. The default policy allows $0.05 a payment, so give this one more with per_payment=0.10.
Paying on Arc takes USDC in Circle Gateway on Arc, and most agents hold theirs on Base or Solana. One command brings it over and deposits it:
cra-agent fund 5 --from base # from this agent's own wallet on Base, same key and address
cra-agent fund 5 --from solana --solana-key-file ~/sol.json # from a Solana wallet: our hex seed or solana-keygen's JSON cra-agent fund 5 --from base --dry-run # everything checked, nothing signed
It asks Eco for a route, and checks the quote before signing anything, from the transaction's own calldata: a CCTP burn of exactly that amount to Arc's domain, minting to this agent, a fee under the cap (--max-fee, default 0.5% or $0.01), the refund to the same wallet. From Base, the vault the USDC goes into must be the one Eco's Portal derives for that intent. It then waits for the USDC on Arc, usually seconds, and deposits it into Gateway, leaving $0.01 in the wallet for Arc's gas (--keep, or --no-deposit to keep it all in the wallet). From Base the wallet needs a little ETH for two transactions, about a cent; from Solana, a little SOL. The model has no tool for this: moving money between chains is the owner's call, from a terminal.
cra-agent find bitcoin price # what is for sale on Arc; needs no key (in a browser: cra-agent.tech/bazaar)
cra-agent balance cra-agent quote https://api.cra-agent.tech/v1/paid/rpc/health cra-agent quote https://api.exa.ai/search --body '{"query":"x402 on Arc"}' # the price of a POST, with its body cra-agent fund 5 --from base # USDC from Base to this agent on Arc, into Gateway cra-agent deposit 1 cra-agent withdraw 1 # Gateway balance back to the wallet; how a seller collects cra-agent pay https://api.cra-agent.tech/v1/paid/rpc/health cra-agent pay https://api.exa.ai/search 0.007 --body '{"query":"x402 on Arc"}' # a POST, refused above the listed price cra-agent think "What is x402, in two sentences?" --budget 0.10 # an agent that pays for its own thinking cra-agent proof cra-agent verify receipt.json # needs no key and no network cra-agent pq-key ~/.cra-agent/pq.key # a post-quantum key for receipts; prints only its public half cra-agent verify receipt.json --require-pq --on-arc # the second signature too, and Arc's own verdict on it
Every receipt carries the limits the payment passed under and is signed with the agent's key, so someone who was not there can check it. The signature proves the agent issued the statement and nobody changed it; the settlement on chain is the independent half.
| Variable | Meaning | |
|---|---|---|
CRA_NETWORK | arc (mainnet) or arcTestnet. Default arcTestnet. | |
CRA_KEY_FILE / CRA_PRIVATE_KEY | The agent's key. Prefer the file. | |
CRA_POLICY | `daily=5,per_seller=0.5,per_payment=0.05,rate=120/60s,allow=a.com\ | b.com,deny=c.com` |
CRA_RPC_URL | Optional, one or several separated by commas, in priority order. Tried before the public Arc endpoints. | |
CRA_RPC_STRICT | 1 to never fall back to a public endpoint. | |
CRA_BASE_RPC_URL / SOLANA_RPC_URL | Optional, for fund: the Base and Solana endpoints. Public ones by default. | |
DATABASE_URL | Optional Postgres for the ledger. Without it the ledger lives in memory. | |
CRA_PQ_KEY_FILE | Optional, the file cra-agent pq-key made. Every receipt is then signed a second time with SLH-DSA-SHA2-128s, the post-quantum scheme Arc verifies on chain. It covers the receipt, not the payment, and adds about a second to each one. |
Two things worth knowing. A payment is settled only after the seller's handler succeeds, so a failing endpoint costs nothing: https://api.cra-agent.tech/v1/paid/selftest/fail always answers 500 so you can check. And identity=required pays only sellers with an ERC-8004 identity on Arc: the address that gets paid must own an agent in the registry, or be the wallet an agent declared for payments. It proves an identity exists, not that the seller is honest; registering costs only gas.
Payments for AI agents on Arc, Circle's USDC-native L1. Site: cra-agent.tech · Source: github.com/giupy997/arcagentx402 · MIT