ClawPay MCP — Non-Custodial x402 Payments for AI Agents

Registre officiel Finance et paiements

Non-custodial x402 payments for AI agents. Sign locally, spend limits, Base network.

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

NPM package clawpay-mcp
Claude Code
claude mcp add clawpay-mcp-non-custodial-x402-payments- -e 'AGENT_PRIVATE_KEY=<your agent_private_key>' -e 'BASE_RPC_URL=<BASE_RPC_URL>' -- npx -y clawpay-mcp@1.1.2
Configuration JSON (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "clawpay-mcp-non-custodial-x402-payments-": {
            "command": "npx",
            "args": [
                "-y",
                "clawpay-mcp@1.1.2"
            ],
            "env": {
                "AGENT_PRIVATE_KEY": "<your agent_private_key>",
                "BASE_RPC_URL": "<BASE_RPC_URL>"
            }
        }
    }
}

Variables d'environnement

  • AGENT_PRIVATE_KEY obligatoire secret Private key for the agent wallet (hex, without 0x prefix)
  • BASE_RPC_URL Base RPC URL (defaults to public Base mainnet)

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. AgentPay MCP
  2. Start without funds
  3. MCP client configuration
  4. Tool groups
  5. Security boundaries
  6. Technical proof index
  7. Verify a clean checkout
  8. Related repositories
  9. Support and disclosure
  10. License

[!WARNING] Paused for security maintenance. Do not use in production.

AgentPay MCP

AgentPay MCP is a stdio Model Context Protocol server for x402 payments and wallet operations. It exposes Agent Wallet SDK functions as MCP tools and loads a caller-controlled signing key from the local process environment.

The current npm package is agentpay-mcp v4.2.0.

Start without funds

Check the installed command without loading wallet credentials:

npx -y agentpay-mcp --version
npx -y agentpay-mcp --help

Use the AgentPay Wallet Starter for a no-funds verification of allowed, approval-required, and blocked policy outcomes.

MCP client configuration

Wallet tools read the following environment variables:

VariableRequired for wallet toolsMeaning
AGENT_PRIVATE_KEYYesLocal hot-wallet signing key
AGENT_WALLET_ADDRESSYesDeployed AgentAccountV2 address
CHAIN_IDNo8453 or 84532; defaults to Base mainnet
RPC_URLNoCaller-selected Base RPC endpoint
FACTORY_ADDRESSFor deploymentWallet factory address
NFT_CONTRACT_ADDRESSFor deploymentToken contract bound to a wallet
SESSION_TTL_SECONDSNoLocal session lifetime in seconds

Example MCP configuration:

{
  "mcpServers": {
    "agentpay": {
      "command": "npx",
      "args": ["-y", "agentpay-mcp"],
      "env": {
        "AGENT_PRIVATE_KEY": "<secret-reference-or-local-key>",
        "AGENT_WALLET_ADDRESS": "0x<deployed-wallet-address>",
        "CHAIN_ID": "84532"
      }
    }
  }
}

Do not commit a real signing key. Use the client or operating system's secret mechanism where one exists. Start on Base Sepolia before using Base mainnet.

Tool groups

The tool registry in src/index.ts exposes these groups:

GroupExamples
Walletdeploy_wallet, get_wallet_info, queue_approval
Paymentssend_payment, x402_pay, x402 session tools
Policyset_spend_policy, check_budget, OTel budget tools
TokensLookup, custom-token registration, balances, and transfers
ExecutionSwap, USDC bridge, and mutual-stake escrow
TrustERC-8004 identity, reputation, and UAID verification
Historyget_transaction_history for wallet contract events

Tool schemas and handlers live under src/tools/.

Security boundaries

These boundaries matter more than the feature list:

  • The server reads AGENT_PRIVATE_KEY into its local Node.js process and uses viem for signing. Protect the process, environment, and MCP client config.
  • set_spend_policy stores policy in the MCP server process. The same agent can call that tool again, and a process restart clears its rolling state.
  • Every current value-moving handler calls the in-process policy check, but this is still application-level enforcement.
  • swap_tokens and bridge_usdc reserve spend at approve, then settle, release, or hold-unknown. Quote, validation, and confirmed uncharged revert failures release the reservation and stay retryable. An unclear post-broadcast outcome locks that intent with no timer.
  • On-chain limits exist only when the wallet owner configures them directly on AgentAccountV2. set_spend_policy does not write those contract limits.
  • An over-limit transaction is a human gate only when the owner key is kept separate from the agent key.
  • get_transaction_history reads on-chain wallet events and, for unscoped all queries, also lists x402 settlements made by this server process (final URL of the paid response, which may differ from the 402 issuer under redirects, method, amount, token, payee, tx hash, replay count). Those x402 receipts mean the payment was broadcast (a tx hash was returned), not that a receipt was confirmed. They are kept in memory only, capped at 256, and lost on restart. They are omitted from block-scoped queries. This is not an MCP request log: it does not record rejected pre-chain attempts or read-only calls.
  • Runtime wallet configuration currently supports Base mainnet and Base Sepolia. Unsupported chain IDs fail closed in src/utils/client.ts.
  • Swap, bridge, escrow, and payment tools can move funds and consume gas. Test with bounded values and independent wallet limits.

Read docs/security-posture.md for the detailed control map and known limitations.

Technical proof index

The repository keeps deeper interoperability and buyer-safety evidence in versioned documents:

AgentPay pins viem exactly at 2.57.4.

The directory comparison was captured against agentpay-mcp@4.1.9; the package version at the top of this README is the current release.

Verify a clean checkout

npm ci
npm run build
npm run typecheck
npm test
npm run lint
npm run security
npm run smoke:clean-install

The CI workflow is separate from scheduled daily review and repair workflows. A scheduled-review failure is not a product-test result, and a repair success does not replace CI.

Support and disclosure

License

MIT. See LICENSE.

Questions fréquentes

Qu'est-ce que ClawPay MCP — Non-Custodial x402 Payments for AI Agents ?

Non-custodial x402 payments for AI agents. Sign locally, spend limits, Base network.

Comment installer ClawPay MCP — Non-Custodial x402 Payments for AI Agents ?

Il s'exécute sur votre machine. Dans Claude Code : claude mcp add clawpay-mcp-non-custodial-x402-payments- -e 'AGENT_PRIVATE_KEY=<your agent_private_key>' -e 'BASE_RPC_URL=<BASE_RPC_URL>' -- npx -y clawpay-mcp@1.1.2. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour ClawPay MCP — Non-Custodial x402 Payments for AI Agents ?

Oui. Il attend AGENT_PRIVATE_KEY, à renseigner dans sa configuration.

ClawPay MCP — Non-Custodial x402 Payments for AI Agents est-il open source ?

Oui. Son code est sur GitHub sous licence MIT.

Qui maintient ClawPay MCP — Non-Custodial x402 Payments for AI Agents ?

Il est publié par up2itnow0822. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.