Provides tools for managing a non-custodial USDC wallet on Base using Coinbase Smart Wallet, enabling AI agents to create and settle payments with human approval.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Grip MCP Show me my Grip wallet"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Give Claude (or any MCP-compatible agent) a non-custodial USDC wallet on Base — with human-in-the-loop approval on every payment.
@grip-foundation/grip-mcp is a Model Context Protocol server that exposes four tools to any MCP-aware client (Claude Desktop, Claude Code, Continue, etc.):
Tool | What it does | Who approves |
| Returns the agent's smart account address + USDC balance on Base. | — |
| Stages a payment (off-chain). Returns an approval token. | — |
| Settles or rejects a staged payment. On approve, executes a real USDC transfer on Base mainnet. | Human, in chat |
| Lists recent payments from the session. | — |
The agent never moves money without you. The flow is: agent stages → you confirm in chat → agent settles. There is no programmatic auto-approve.
Related MCP server: cardzero-mcp
npx (after first publish)In ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %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 buildThen point Claude Desktop at the built file:
{
"mcpServers": {
"grip": {
"command": "node",
"args": ["/absolute/path/to/grip-mcp/dist/server/index.js"]
}
}
}Restart Claude Desktop after editing the config.
The first time the server starts, it generates a brand-new EOA private key and stores it at ~/.grip-mcp/agent-key (mode 0600). This key controls the smart account.
In Claude, ask:
Show me my Grip wallet
Claude will call grip_wallet and reply with your smart account address, balance, and limits. Send USDC on Base to that address to fund.
Once funded, ask Claude something like:
Send 5 USDC to 0xba14744FfD57FA7d03b20D4c8BeDAaC301E865d1
Claude will:
Call grip_create_payment to stage the payment off-chain.
Show you the details (amount, recipient, memo) and ask for confirmation.
Wait for your reply.
If you say "approve" → call grip_settle_payment(token, "approve") → executes on Base.
If you say "no" → call grip_settle_payment(token, "reject") → no on-chain action.
Tx hash + Basescan link are returned on settlement.
Env var | Default | What it does |
| (auto-generate) | Override the agent's signer private key. Useful for restoring a wallet across machines. |
|
| Where the auto-generated key is stored. |
|
| Maximum USDC per single payment. |
|
| Maximum USDC across all payments per UTC day. |
Non-custodial. The Grip Foundation does not hold your keys, your USDC, or any record of your payments. Everything runs on your machine.
Managed paymaster, no signup. Gas is paid in USDC via the Pimlico paymaster routed through Grip's hosted proxy. You don't need a Pimlico account.
Human-in-the-loop is enforced by the protocol, not the model. grip_create_payment only stages. grip_settle_payment is a separate tool call. Most MCP clients (Claude Desktop included) prompt for human confirmation before executing tool calls — that's a second layer of gating.
Caps are enforced server-side. Even if the model attempts a payment over your per-tx or daily cap, the server refuses to stage it.
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)The smart account is a Coinbase Smart Wallet (ERC-4337) on Base. The first payment from a fresh wallet runs a one-time bootstrap UserOp that deploys the account and approves the paymaster for USDC reimbursement; subsequent UserOps are USDC-paid.
First payment may need a retry. In @grip-labs/sdk@0.4, the bootstrap UserOp (deploy + paymaster approve) and the actual transfer UserOp are submitted as two separate operations. There's a small race window where viem's internal getFactoryArgs() reads stale getCode from the public RPC after bootstrap has settled at the Pimlico bundler — viem then includes initCode in the second UserOp and the bundler rejects it with AA10 sender already constructed.
If your first payment fails with that error, simply ask the agent to retry. The retry succeeds because the on-chain state has propagated by then. Subsequent payments from the same wallet are clean — bootstrap runs at most once per wallet.
A fix is shipping in @grip-labs/sdk@0.5 that consolidates bootstrap + first transfer into a single sponsored UserOp using executeBatch, eliminating the race by construction and saving ~30% gas on the first payment. grip-mcp will pick it up in 0.1.1.
MIT
Grip Foundation · open identity + payments rails for AI agents.
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. Dates show when Glama detected each change.
v0.1.0grip_create_paymentgrip_list_paymentsgrip_settle_paymentgrip_walletEach 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.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Cash out an AI agent's USDC to a real bank account (non-custodial). Plus Base data + a marketplace
Payment infrastructure for AI agents: spending rules, approval flows, single-use virtual cards.
Agent-to-agent escrow on Base. Post quests with ETH/USDC bounties and settle on-chain.
Risk regime + treasury for AI agents on Base: free regime reads, signed attestations, idle USDC.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/grip-foundation/grip-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
