Предоставьте Claude (или любому другому агенту, совместимому с MCP) некастодиальный кошелек USDC в сети Base — с обязательным подтверждением каждого платежа человеком.
@grip-foundation/grip-mcp — это сервер Model Context Protocol, который предоставляет четыре инструмента любому клиенту с поддержкой MCP (Claude Desktop, Claude Code, Continue и т. д.):
Инструмент | Что он делает | Кто подтверждает |
| Возвращает адрес смарт-аккаунта агента + баланс USDC в сети Base. | — |
| Подготавливает платеж (вне сети). Возвращает токен подтверждения. | — |
| Проводит или отклоняет подготовленный платеж. При подтверждении выполняет реальный перевод USDC в основной сети Base. | Человек, в чате |
| Выводит список недавних платежей за сессию. | — |
Агент никогда не переводит деньги без вашего участия. Процесс выглядит так: агент подготавливает платеж → вы подтверждаете его в чате → агент завершает транзакцию. Программного автоматического подтверждения не существует.
Related MCP server: @arispay/payagent-mcp
npx (после первой публикации)В файле ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) или %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"grip": {
"command": "npx",
"args": ["-y", "@grip-foundation/grip-mcp"]
}
}
}git clone https://github.com/grip-foundation/grip-mcp.git
cd grip-mcp
pnpm install
pnpm run buildЗатем укажите Claude Desktop путь к собранному файлу:
{
"mcpServers": {
"grip": {
"command": "node",
"args": ["/absolute/path/to/grip-mcp/dist/server/index.js"]
}
}
}После редактирования конфигурации перезапустите Claude Desktop.
При первом запуске сервер генерирует совершенно новый закрытый ключ EOA и сохраняет его в ~/.grip-mcp/agent-key (режим 0600). Этот ключ управляет смарт-аккаунтом.
В Claude спросите:
Show me my Grip wallet
Claude вызовет grip_wallet и ответит, указав адрес вашего смарт-аккаунта, баланс и лимиты. Чтобы пополнить кошелек, отправьте USDC в сети Base на этот адрес.
После пополнения счета попросите Claude о чем-то вроде:
Send 5 USDC to 0xba14744FfD57FA7d03b20D4c8BeDAaC301E865d1
Claude сделает следующее:
Вызовет grip_create_payment для подготовки платежа вне сети.
Покажет вам детали (сумма, получатель, примечание) и попросит подтверждения.
Будет ждать вашего ответа.
Если вы скажете "approve" → вызовет grip_settle_payment(token, "approve") → выполнит транзакцию в сети Base.
Если вы скажете "no" → вызовет grip_settle_payment(token, "reject") → никаких действий в сети не будет.
Хэш транзакции и ссылка на Basescan будут возвращены после завершения платежа.
Переменная окружения | По умолчанию | Что она делает |
| (автогенерация) | Переопределяет закрытый ключ подписи агента. Полезно для восстановления кошелька на разных устройствах. |
|
| Путь, где хранится автоматически сгенерированный ключ. |
|
| Максимальная сумма USDC за один платеж. |
|
| Максимальная сумма USDC для всех платежей в течение суток (UTC). |
Некастодиальность. Grip Foundation не хранит ваши ключи, ваши USDC или какие-либо записи о ваших платежах. Все работает на вашем устройстве.
Управляемый пеймастер, без регистрации. Комиссия за газ оплачивается в USDC через пеймастер Pimlico, маршрутизируемый через прокси-сервер Grip. Вам не нужна учетная запись Pimlico.
Участие человека обеспечивается протоколом, а не моделью. grip_create_payment только подготавливает платеж. grip_settle_payment — это отдельный вызов инструмента. Большинство MCP-клиентов (включая Claude Desktop) запрашивают подтверждение человека перед выполнением вызовов инструментов — это второй уровень защиты.
Лимиты принудительно устанавливаются на стороне сервера. Даже если модель попытается совершить платеж, превышающий ваш лимит на транзакцию или дневной лимит, сервер откажется его подготавливать.
Claude Desktop
│ MCP (stdio)
▼
grip-mcp (this server)
│ @grip-labs/sdk
▼
Grip-managed paymaster proxy → Pimlico bundler → Base mainnet
▲
Coinbase Smart Wallet
(your smart account)Смарт-аккаунт — это Coinbase Smart Wallet (ERC-4337) в сети Base. Первый платеж с нового кошелька запускает однократную операцию UserOp для развертывания аккаунта и одобрения пеймастера для компенсации USDC; последующие UserOp оплачиваются в USDC.
Первый платеж может потребовать повторной попытки. В @grip-labs/sdk@0.4 начальная UserOp (развертывание + одобрение пеймастера) и фактическая UserOp перевода отправляются как две отдельные операции. Существует небольшое окно состояния гонки, когда внутренний метод viem getFactoryArgs() считывает устаревшие данные getCode из публичного RPC после того, как начальная операция была подтверждена в бандлере Pimlico — затем viem включает initCode во вторую UserOp, и бандлер отклоняет ее с ошибкой AA10 sender already constructed.
Если ваш первый платеж завершился с этой ошибкой, просто попросите агента повторить попытку. Повторная попытка будет успешной, так как состояние в сети к тому времени обновится. Последующие платежи с того же кошелька проходят без проблем — начальная настройка выполняется не более одного раза для каждого кошелька.
Исправление будет включено в @grip-labs/sdk@0.5, которое объединяет начальную настройку и первый перевод в одну спонсируемую UserOp с использованием executeBatch, что исключает состояние гонки по определению и экономит около 30% газа на первом платеже. grip-mcp получит это обновление в версии 0.1.1.
MIT
Grip Foundation · открытая инфраструктура идентификации и платежей для ИИ-агентов.
Stages a payment from the agent's Grip wallet to a recipient. DOES NOT execute on-chain. Returns an approval_token. You MUST then show the payment details (amount, recipient, memo) to the human in plain language and ASK FOR EXPLICIT CONFIRMATION before calling grip_settle_payment. Never auto-approve. The human must say 'approve' (or equivalent) before settling. If they say 'no', call grip_settle_payment with decision='reject'.
| Name | Required | Description | Default |
|---|---|---|---|
| recipient | Yes | ||
| amount_usdc | Yes | ||
| memo | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that the tool does not execute on-chain, returns an approval_token, and requires a two-step human approval process. This adds significant context beyond annotations (which only indicate non-read-only and non-destructive). No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, front-loaded with the core purpose, and structured logically: action, caution, required follow-up steps. Every sentence serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite lacking an output schema, the description explains the return value (approval_token) and the complete workflow (stage, confirm, settle/reject). It references sibling tools and provides enough context for a complex, multi-step tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description mentions 'amount, recipient, memo' but does not elaborate on schema constraints like the Ethereum address pattern or USDC amount limits. With 0% schema description coverage, the description adds minimal value over the schema itself.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that this tool stages a payment without executing on-chain, distinguishing it from sibling tools like grip_settle_payment. It specifies the action ('create pending payment') and resource ('agent's Grip wallet to recipient').
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs the agent to never auto-approve, to show payment details to the human, and to ask for explicit confirmation before calling grip_settle_payment. It also covers the rejection case ('If they say 'no', call grip_settle_payment with decision='reject'').
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns recent payments (pending, settled, rejected, failed) staged or executed in this MCP session. Read-only. Useful when the human asks 'what have I paid today' or 'what's pending'.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, destructiveHint, and idempotentHint. The description adds 'Read-only' (consistent) and specifies session-scoped payments, which is not in annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first states purpose and resource, second gives usage examples. No wasted words, front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple tool (one optional parameter, rich annotations, no output schema), the description covers purpose, scope, and use cases adequately.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage for the limit parameter, and the description does not mention the parameter or add meaning beyond the schema's min/max constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'returns' and the resource 'payments', specifying they are 'staged or executed in this MCP session', which distinguishes it from sibling tools like grip_create_payment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidance with examples like 'what have I paid today' or 'what's pending', but does not mention when not to use it or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Executes the on-chain transfer for a previously-staged payment, or marks it as rejected. ONLY call this after the human has explicitly confirmed (or declined) the payment in plain language. If the human has not confirmed, do not call this tool. On approve, this performs a real USDC transfer on Base mainnet via the Pimlico paymaster — it is irreversible.
| Name | Required | Description | Default |
|---|---|---|---|
| approval_token | Yes | ||
| decision | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (destructiveHint=true, idempotentHint=true), the description adds critical context: 'performs a real USDC transfer on Base mainnet via Pimlico paymaster — it is irreversible'. This fully discloses the irreversible and destructive nature.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with no wasted words. The first sentence covers the primary action, and subsequent sentences add critical usage guidance and behavioral context. Highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's destructive and irreversible nature, the description provides essential context (on-chain transfer, paymaster). However, the lack of parameter detail for 'approval_token' means the agent may lack complete information to use the tool correctly. Minor gap prevents a 5.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description does not adequately explain the 'approval_token' parameter (e.g., format, source). It only mentions 'decision' with enum values, leaving a significant gap for the agent to understand how to obtain or use the approval_token.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it executes an on-chain transfer or marks a payment as rejected, with specific verb 'executes' and resource 'previously-staged payment'. It distinguishes from siblings like grip_create_payment and grip_list_payments by focusing on settlement.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states to call only after human confirmation, with a clear prohibition ('do not call this tool') if not confirmed. This provides excellent guidance on when to use vs. not use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns this agent's Grip Pay wallet address (Base mainnet smart account) and current USDC balance. Use this when the human asks about the wallet, where to fund it, how much USDC the agent has, or before suggesting any payment.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds behavioral context by detailing the returned data (wallet address and USDC balance), which is valuable beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, consisting of two short sentences. The key purpose is front-loaded, and there is no unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and the simplicity of the tool, the description covers the essential aspects: what it returns and when to use it. It could be slightly improved by mentioning the format of the output, but it is largely complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters, and the description does not need to add parameter information. The baseline score of 4 is appropriate given 100% schema description coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool returns the agent's wallet address and USDC balance. It uses a specific verb ('Returns') and resource ('wallet info'), and the purpose is distinct from sibling tools which deal with payments.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly lists scenarios when to use the tool: when the human asks about the wallet, where to fund it, how much USDC the agent has, or before suggesting any payment. This provides clear guidance without needing to mention alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0grip_create_paymentgrip_list_paymentsgrip_settle_paymentgrip_walletScored across 4 tools
Each tool has a clear, distinct purpose: creating staged payments, listing payments, settling/rejecting, and checking wallet info. No overlap or ambiguity.
All tools start with 'grip_' and most follow a verb_noun pattern (create_payment, list_payments, settle_payment). The exception is 'grip_wallet', which is a noun phrase, but the inconsistency is minor given the small set.
Four tools is well-scoped for a payment/wallet MCP server. It covers staging, settling, listing, and wallet info without being too few or excessive.
The tool surface covers the core payment workflow: create, settle/reject, list, and wallet info. A potential minor gap is lack of explicit cancellation for staged payments, but the reject option in settle effectively handles that.
Give AI agents a wallet with a spending limit. Non-custodial USDC on Base, server-enforced limits.
Monetization and execution gateway for autonomous AI agents on Base Mainnet
Crypto wallet for AI agents: balances, payments, swaps and trading with owner controls.
Marketplace for AI agents: hire, sell, get paid in USDC on Base. Identity, jobs, reputation.
