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)
Wallet for AI agents with on-chain spending limits and owner approval over the limit
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。
PURSER_RPC_URL, PURSER_ACCOUNT, PURSER_AGENT_PRIVATE_KEY, PURSER_BUNDLER_URL, PURSER_RELAYER_PRIVATE_KEY, PURSER_API_TOKEN「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": {
"purser": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PURSER_RPC_URL",
"-e",
"PURSER_ACCOUNT",
"-e",
"PURSER_AGENT_PRIVATE_KEY",
"-e",
"PURSER_BUNDLER_URL",
"-e",
"PURSER_RELAYER_PRIVATE_KEY",
"-e",
"PURSER_API_TOKEN",
"ghcr.io/ahmad-codex/purser:0.1.2"
],
"env": {
"PURSER_RPC_URL": "your-value",
"PURSER_ACCOUNT": "your-value",
"PURSER_AGENT_PRIVATE_KEY": "your-value",
"PURSER_BUNDLER_URL": "your-value",
"PURSER_RELAYER_PRIVATE_KEY": "your-value",
"PURSER_API_TOKEN": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add purser --env PURSER_RPC_URL=your-value --env PURSER_ACCOUNT=your-value --env PURSER_AGENT_PRIVATE_KEY=your-value --env PURSER_BUNDLER_URL=your-value --env PURSER_RELAYER_PRIVATE_KEY=your-value --env PURSER_API_TOKEN=your-value -- docker run -i --rm -e PURSER_RPC_URL -e PURSER_ACCOUNT -e PURSER_AGENT_PRIVATE_KEY -e PURSER_BUNDLER_URL -e PURSER_RELAYER_PRIVATE_KEY -e PURSER_API_TOKEN ghcr.io/ahmad-codex/purser:0.1.2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": {
"purser": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PURSER_RPC_URL",
"-e",
"PURSER_ACCOUNT",
"-e",
"PURSER_AGENT_PRIVATE_KEY",
"-e",
"PURSER_BUNDLER_URL",
"-e",
"PURSER_RELAYER_PRIVATE_KEY",
"-e",
"PURSER_API_TOKEN",
"ghcr.io/ahmad-codex/purser:0.1.2"
],
"env": {
"PURSER_RPC_URL": "your-value",
"PURSER_ACCOUNT": "your-value",
"PURSER_AGENT_PRIVATE_KEY": "your-value",
"PURSER_BUNDLER_URL": "your-value",
"PURSER_RELAYER_PRIVATE_KEY": "your-value",
"PURSER_API_TOKEN": "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": {
"purser": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PURSER_RPC_URL",
"-e",
"PURSER_ACCOUNT",
"-e",
"PURSER_AGENT_PRIVATE_KEY",
"-e",
"PURSER_BUNDLER_URL",
"-e",
"PURSER_RELAYER_PRIVATE_KEY",
"-e",
"PURSER_API_TOKEN",
"ghcr.io/ahmad-codex/purser:0.1.2"
],
"env": {
"PURSER_RPC_URL": "your-value",
"PURSER_ACCOUNT": "your-value",
"PURSER_AGENT_PRIVATE_KEY": "your-value",
"PURSER_BUNDLER_URL": "your-value",
"PURSER_RELAYER_PRIVATE_KEY": "your-value",
"PURSER_API_TOKEN": "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。
PURSER_BUNDLER_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6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 ahmad-codex 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:PURSER_RPC_URL, PURSER_ACCOUNT, PURSER_AGENT_PRIVATE_KEY, PURSER_RELAYER_PRIVATE_KEY, PURSER_API_TOKEN
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(0.1.2)がレジストリに届いたのは5 日前です。
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Dockerも必要です。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, Reelsaw
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.
Drive a self-hosted Reelsaw: turn long videos into vertical clips, edit, re-render and export them.
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。
Give an AI agent a wallet without giving it your keys.
Purser is an ERC-4337 smart account where each agent gets its own session key with a policy: which contracts and functions it may call, how much it may spend per payment and per day, and until when. Payments inside the policy go through on their own. Anything over the limits waits for you to approve. An MCP server lets Claude, Cursor or any MCP client use the wallet, and a console shows budgets, spending and pending approvals as they happen.
Agents are starting to pay for things: API credits, compute, data, subscriptions. Today that usually means one of two bad options:
Purser sits in between. The limits live in the contract, so they hold even if the agent, the server it runs on, or its key is compromised. The worst a leaked agent key can do is spend the rest of the current budget at allowed places, and burn some ETH on gas, until you revoke it or freeze the account, which takes one transaction. (A gas budget per key is on the roadmap.)
| Layer | What it shows |
|---|---|
| Smart contracts | ERC-4337 v0.7 account with session keys, allow-lists, per-transaction caps and rolling budgets; owner co-signature for over-limit operations; UUPS upgrades, ERC-1271, CREATE2 factory with the same address on every chain |
| Protocol rules | Validation that follows ERC-7562 (no clock reads), so public bundlers accept it; time-based budgets moved to the execution phase through executeUserOp |
| Testing | 41 unit tests through a real EntryPoint, fuzz tests against a budget model, invariant tests with a stateful handler, gas snapshot, Slither in CI |
| TypeScript SDK | viem client that builds, signs and submits user operations through a bundler or handleOps, decodes policy errors, and indexes events within public RPC log limits |
| AI integration | MCP server (streamable HTTP and stdio) with six tools, model-readable refusals, and a human-in-the-loop approval flow |
| Product | React console with budget meters, live activity, approvals, revoke and a kill switch |
| Delivery | One-command demo image, Docker Compose, CI that plays the full story end to end, testnet deploy script |
flowchart LR
Agent["AI agent (Claude, Cursor, ...)"] -- MCP tools --> Server["Purser server holds the session key only"] Server -- "user operation signed by the session key" --> EP["EntryPoint v0.7"] EP --> Wallet["PurserAccount policy checks"] Wallet --> Targets["Allowed contracts and recipients"] Owner["Owner"] -- "approve, reject, revoke, freeze" --> Console["Console"] Console --> Server
(contract, function) pairs, a per-transaction cap and a per-period budget for each token (ETH or ERC-20), and a validity window.send_eth or call_contract. The server dry-runs the call against the policy, signs a user operation with the session key and submits it.executeUserOp.You need Docker. Nothing to clone, nothing to install:
docker run --rm -it -p 127.0.0.1:8787:8787 ghcr.io/ahmad-codex/purser:demo
The container starts a local chain, deploys the EntryPoint, the factory and a fresh account with a seeded agent, and starts the MCP server and the console. Open http://localhost:8787 and watch: ten seconds later the agent story plays in the terminal while the console updates live.
The agent pays a merchant, pays in a token, buys from a shop contract, tries a payment over the limit (the approval request appears in the console), gets approved, is refused for a recipient that is not on its allow-list, and is stopped by the kill switch. Then the wallet stays up for your own agent. Everything uses Anvil's public development keys and is gone when you press Ctrl+C.
From a clone, docker compose up runs the same stack as separate services, and docker compose run --rm demo plays the story against it.
With the demo running, point any MCP client at http://localhost:8787/mcp:
claude mcp add --transport http purser http://localhost:8787/mcp
Then ask Claude: *"Check the wallet status, then pay the merchant 0.01 ETH for API credits."* Try *"pay the merchant 0.3 ETH"* to see an approval request show up in the console. docs/mcp-clients.md covers Claude Desktop, Cursor and stdio.
| Tool | What it does |
|---|---|
wallet_status | Balances, the agent's remaining budget per token, caps, reset times, expiry, freeze state, pending approvals |
send_eth | Pay ETH to an address or a known name |
send_token | Pay ERC-20 tokens by symbol or address |
call_contract | Call an allowed contract function, optionally with ETH, e.g. buy(uint256) |
get_request | Status of an approval request |
list_requests | Recent approval requests |
Each payment tool returns one of: done (with the transaction hash and the budget left), waiting for the owner (with the request id), or refused (with a reason the model can act on).
| Field | Meaning |
|---|---|
permissions | (target, selector) pairs. 0xffffffff allows any function on a target; 0x00000000 allows plain ETH transfers. The account itself can never be a target. |
limits | Per token (address(0) is ETH): perTx cap and perPeriod budget. ERC-20 transfer, approve and transferFrom from the account count as spending. |
period | Budget window in seconds, for example 86400 for a daily budget. |
validAfter, validUntil | When the key works. Enforced by the EntryPoint through the validation data. |
Granting a key again replaces its whole policy; old permissions do not leak into the new one.
| Contract | Purpose |
|---|---|
PurserAccount | The account: ERC-4337 v0.7, UUPS upgradeable by its owner, ERC-1271, token callbacks |
PurserFactory | CREATE2 factory, so an account's address is known before it is deployed |
Built on the eth-infinitism reference EntryPoint v0.7 and OpenZeppelin 5. The factory deploys through the deterministic CREATE2 proxy, so it has the same address on every chain with the canonical EntryPoint.
Tests. 41 unit tests through a real EntryPoint, fuzz tests that check random payment and time sequences against a model of the budget, and invariant tests (about 16,000 random calls per run) for three properties: an agent never spends more than its budget per period without approval, a revoked key never moves funds again, and the policy never changes behind the owner's back. Slither runs in CI. See docs/security.md for the threat model.
Deployments. See docs/deployments.md.
contracts/ Foundry project: PurserAccount, factory, tests, deploy and demo scripts
packages/sdk/ TypeScript client on viem: build, sign and send user operations, read state packages/server/ MCP server (HTTP and stdio), approvals API, serves the console apps/console/ React console for the owner scripts/ local-up.sh, deploy-testnet.sh, demo.ts, demo-entrypoint.sh Dockerfile.demo all-in-one demo image (chain, contracts, server, console) docs/ architecture, security, MCP clients, deployments
npm install
cd contracts && forge test # unit, fuzz and invariant tests cd .. && npm test # TypeScript unit tests ./scripts/local-up.sh # Anvil + deploy + demo account, writes .env.local npm run build -w @purser/console npm run server # console and MCP on http://localhost:8787 npm run demo # the end-to-end story; CI runs it too
No Foundry installed? contracts/forge.sh forge test runs it from the official Docker image, and scripts/local-up.sh falls back to Docker on its own.
To deploy to Base Sepolia or Sepolia, see docs/deployments.md: one script, and a faucet drip of under 0.01 ETH covers everything.
Early, version 0.1.2. Not audited. Use testnets, and do not put real funds in an account you have not reviewed yourself. What is planned next is in ROADMAP.md, and issues labelled good first issue are a good place to start contributing.
See CONTRIBUTING.md. Security reports go through private advisories, not issues.
MIT