Dale a Claude (o a cualquier agente compatible con MCP) una billetera USDC sin custodia en Base, con aprobación humana en cada pago.
@grip-foundation/grip-mcp es un servidor del Protocolo de Contexto de Modelo (MCP) que expone cuatro herramientas a cualquier cliente compatible con MCP (Claude Desktop, Claude Code, Continue, etc.):
Herramienta | Qué hace | Quién aprueba |
| Devuelve la dirección de la cuenta inteligente del agente + saldo de USDC en Base. | — |
| Prepara un pago (fuera de la cadena). Devuelve un token de aprobación. | — |
| Liquida o rechaza un pago preparado. Al aprobar, ejecuta una transferencia real de USDC en la red principal de Base. | Humano, en el chat |
| Enumera los pagos recientes de la sesión. | — |
El agente nunca mueve dinero sin ti. El flujo es: el agente prepara → tú confirmas en el chat → el agente liquida. No existe la autoaprobación programática.
Related MCP server: @arispay/payagent-mcp
npx (después de la primera publicación)En ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) o %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 buildLuego apunta Claude Desktop al archivo compilado:
{
"mcpServers": {
"grip": {
"command": "node",
"args": ["/absolute/path/to/grip-mcp/dist/server/index.js"]
}
}
}Reinicia Claude Desktop después de editar la configuración.
La primera vez que se inicia el servidor, genera una clave privada EOA nueva y la almacena en ~/.grip-mcp/agent-key (modo 0600). Esta clave controla la cuenta inteligente.
En Claude, pregunta:
Muéstrame mi billetera Grip
Claude llamará a grip_wallet y responderá con la dirección de tu cuenta inteligente, el saldo y los límites. Envía USDC en Base a esa dirección para fondearla.
Una vez fondeada, pídele a Claude algo como:
Envía 5 USDC a 0xba14744FfD57FA7d03b20D4c8BeDAaC301E865d1
Claude hará lo siguiente:
Llamará a grip_create_payment para preparar el pago fuera de la cadena.
Te mostrará los detalles (cantidad, destinatario, nota) y pedirá confirmación.
Esperará tu respuesta.
Si dices "aprobar" → llamará a grip_settle_payment(token, "approve") → se ejecuta en Base.
Si dices "no" → llamará a grip_settle_payment(token, "reject") → no se realiza ninguna acción en la cadena.
El hash de la transacción y el enlace a Basescan se devuelven al liquidar.
Variable de entorno | Predeterminado | Qué hace |
| (autogenerado) | Sobrescribe la clave privada del firmante del agente. Útil para restaurar una billetera en diferentes máquinas. |
|
| Dónde se almacena la clave autogenerada. |
|
| USDC máximo por pago individual. |
|
| USDC máximo en todos los pagos por día UTC. |
Sin custodia. La Fundación Grip no guarda tus claves, tu USDC ni ningún registro de tus pagos. Todo se ejecuta en tu máquina.
Paymaster gestionado, sin registro. El gas se paga en USDC a través del paymaster de Pimlico enrutado mediante el proxy alojado de Grip. No necesitas una cuenta de Pimlico.
El factor humano es impuesto por el protocolo, no por el modelo. grip_create_payment solo prepara. grip_settle_payment es una llamada de herramienta separada. La mayoría de los clientes MCP (incluido Claude Desktop) solicitan confirmación humana antes de ejecutar llamadas de herramientas; esa es una segunda capa de control.
Los límites se aplican en el lado del servidor. Incluso si el modelo intenta un pago que supera tu límite por transacción o diario, el servidor se negará a prepararlo.
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)La cuenta inteligente es una Coinbase Smart Wallet (ERC-4337) en Base. El primer pago desde una billetera nueva ejecuta un UserOp de arranque único que despliega la cuenta y aprueba el paymaster para el reembolso de USDC; los UserOps posteriores se pagan con USDC.
El primer pago puede requerir un reintento. En @grip-labs/sdk@0.4, el UserOp de arranque (despliegue + aprobación de paymaster) y el UserOp de transferencia real se envían como dos operaciones separadas. Existe una pequeña ventana de carrera donde getFactoryArgs() interno de viem lee un getCode obsoleto del RPC público después de que el arranque se haya liquidado en el bundler de Pimlico; viem entonces incluye initCode en el segundo UserOp y el bundler lo rechaza con AA10 sender already constructed.
Si tu primer pago falla con ese error, simplemente pídele al agente que lo intente de nuevo. El reintento tiene éxito porque el estado en la cadena se ha propagado para entonces. Los pagos posteriores desde la misma billetera son limpios: el arranque se ejecuta como máximo una vez por billetera.
Se está lanzando una corrección en @grip-labs/sdk@0.5 que consolida el arranque + la primera transferencia en un único UserOp patrocinado usando executeBatch, eliminando la carrera por construcción y ahorrando aproximadamente un 30% de gas en el primer pago. grip-mcp lo incluirá en la versión 0.1.1.
MIT
Grip Foundation · identidad abierta + rieles de pago para agentes de IA.
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.
