x402 Agent Tollbooth

io.github.ak10082247-maxPublished by GitHub account ak10082247-maxv2.1.0Updated Oct 26, 2026

On-chain DeFi smart contract auditor, arbitrage scanner, and agent tollbooth via x402 on Base.

VerifiedStreamable HTTPWeb executableFinanceSecurity & MonitoringAI & ML

Overview

AI-generated overview

Paid Web3 intelligence MCP server on Base: AI smart contract audits, cross-DEX arbitrage scans, routing, and agent memory, billed per call in USDC via x402.

What you can do
  • Audit and scan Base smart contracts and code for vulnerabilities, with a free teaser scan before paid deep dives
  • Scan Uniswap, Aerodrome and BaseSwap pools for cross-DEX arbitrage and liquidity opportunities
  • Compute gas- and slippage-optimized execution routes for agents and automated executors
  • Store and retrieve persistent agent memory and query the service's underlying LLM
  • Each paid tool requires a USDC payment authorization on Base or Solana, with an optional referral wallet for fee sharing
When to use it
Worth adding when an agent needs on-chain security review, arbitrage or routing intelligence on Base and you are prepared to pay small per-call USDC fees. Not needed for general code review or non-Web3 work.
Requirements
Remote streamable HTTP endpoint; no account or API key is declared. Paid tools require a Base or Solana wallet able to sign USDC payment authorizations (x402), and the README's self-hosting path needs Docker or Python plus a GEMINI_API_KEY.
Before you install
Every paid tool spends real USDC per call, from 0.001 to 0.02 USDC in the tool list and up to 10 USDC for other services in the README. The bundled FastPass SDK asks for your agent's wallet private key, and the README's sample code signs payment authorizations with it; use a dedicated low-balance wallet. Requests and wallet addresses go to a third-party hosted service.

Installation

In SourceWeft

  1. Open x402 Agent Tollbooth in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.ak10082247-max%2Fx402-agent-tollbooth/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "x402-agent-tollbooth": {
      "type": "http",
      "url": "https://x402-agent-tollbooth.onrender.com/mcp"
    }
  }
}

README

🛣️ x402 Agent Tollbooth

The x402 Agent Tollbooth is an enterprise-grade Model Context Protocol (MCP) server that demonstrates machine-to-machine (M2M) micro-transactions on the Base network.

This project provides an infrastructure layer allowing AI agents to programmatically access specialized Web3 intelligence and smart contract analysis tools by fulfilling automated HTTP 402 (Payment Required) workflows via the x402 protocol standard. Agents pay per tool execution directly in USDC, enabling a seamless, trustless API monetization model.

[Smithery Quality Score: 100/100] [Network] [Currency] [Glama]


💻 Open Source Implementation & Self-Hosting

This repository contains the full, open-source Python implementation of the MCP server. The server is built using the official mcp SDK and sse-starlette to handle Server-Sent Events (SSE) and JSON-RPC tool calling.

The core implementation is located in tollbooth_agent.py.

Running from Source (Local Execution)

You can easily self-host this MCP server or run it locally for your own agents.

Using Docker:

bash
docker build -t x402-tollbooth .docker run -p 8000:8000 -e GEMINI_API_KEY="your_api_key" x402-tollbooth

Using Python:

bash
pip install -r requirements.txtuvicorn tollbooth_agent:mcp_app --host 0.0.0.0 --port 8000

🛠️ Server Capabilities

This server exposes a navigable tree of specialized Web3 tools. AI agents must provide a valid Base network paymentHash (transaction receipt) for the exact USDC amount required to execute the paid tools.

🤝 Referral Revenue Sharing Protocol: The server implements an optional referralWallet parameter. AI agents acting as intermediaries can append their wallet address to receive a 20% protocol fee distribution.

🆓 Infrastructure & Discovery

  • contract.auditTeaser (FREE): Scans a Base smart contract for vulnerabilities and returns a high-level summary. Designed to allow agents to assess necessity before authorizing paid deep-dives.

📊 Token Data & Intelligence

  • token.analyze (0.50 USDC): Real-time liquidity, volume, and analytics for any Base token. Aggregates data for high-frequency algorithmic usage.

🔐 Smart Contract Security

  • contract.audit (1.00 USDC): Full AI-driven smart contract vulnerability audit. Returns exact lines of code, risk severity, and attack vectors.
  • contract.patch (5.00 USDC): Premium service. Audits the contract and generates production-ready, secure Solidity code to patch the vulnerabilities.

🧠 Market Intelligence

  • market.alpha (10.00 USDC): High-level metadata brokering. Aggregates metadata to reveal which smart contracts are currently experiencing high automated analysis volume on the network.
  • wallet.profile (2.00 USDC): Behavioral finance AI analysis of a specific wallet address. Generates risk profiles and portfolio strategies based on public on-chain actions.

💾 Agent Persistence

  • memory.store (0.01 USDC): Persistent memory bank for agents to store context across sessions.
  • memory.retrieve (0.01 USDC): Retrieve stored contextual memory.
  • llm.query (0.10 USDC): Query the Tollbooth's underlying LLM directly for complex reasoning tasks.

⚡ The X402 FastPass SDK (Seamless Agent Integration)

If you are building custom AI agents in LangChain, AutoGen, or CrewAI, you do not need to teach your LLMs how to write Web3 transactions to use this server.

We have included the X402 FastPass SDK (x402_fastpass.py) directly in this repository. It acts as a wrapper around the MCP client and automatically handles the USDC crypto payments natively in Python.

How to give your agent seamless access:

python
from x402_fastpass import X402FastPassimport asyncio
# 1. Give the FastPass Client your agent's Base wallet private keyclient = X402FastPass(private_key="0xYOUR_PRIVATE_KEY")
# 2. Give this Python function to your agent as a standard tool.# The SDK automatically handles the on-chain USDC transfer and passes the payment hash to the MCP server!async def run_audit():    result = await client.audit_contract("0xTargetSmartContractAddress")    print(result)
asyncio.run(run_audit())

Note: The FastPass SDK automatically injects your agent's wallet address as the referralWallet, meaning your agent automatically earns a 20% cashback on all tools it calls!


⚙️ How it Works: Modern x402 V2 Header Handshake (100% Gasless)

The server supports the official x402 V2 specification with 100% gasless settlement on Base Mainnet (eip155:8453) and Solana Mainnet (solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp):

  1. Unpaid Probe: Agent calls endpoint (e.g. POST /toll/cross-dex-arbitrage). Server immediately returns HTTP 402 Payment Required with a 50% Free Teaser Preview and PAYMENT-REQUIRED header challenge.
  2. Auto-Sign (Zero Gas): Agent signs an EIP-712 TransferWithAuthorization (on Base) or partially-signs an SPL TransferChecked (on Solana). The relayer facilitator sponsors all gas fees ($0 ETH / $0 SOL required).
  3. Replay & Unlock: Agent attaches Base64 PAYMENT-SIGNATURE header. Server verifies via facilitator in <10ms and returns HTTP 200 OK with full unredacted intel and PAYMENT-RESPONSE cryptographic receipt.

Autonomous Agent Auto-Pay (Python)

python
import base64, json, secrets, time, requestsfrom eth_account import Accountfrom eth_account.messages import encode_typed_data
def paid_toll_call(endpoint: str, payload: dict, private_key: str):    account = Account.from_key(private_key)    url = f"https://x402-agent-tollbooth.onrender.com{endpoint}"
    # 1. Probe endpoint    res = requests.post(url, json=payload)    if res.status_code == 200:        return res.json()
    # 2. Decode 402 challenge & sign EIP-712 authorization    raw_pr = res.headers.get("PAYMENT-REQUIRED") or res.headers.get("X-Payment-Required")    pr_json = json.loads(base64.b64decode(raw_pr).decode("utf-8"))    accepted = next(a for a in pr_json["accepts"] if "8453" in str(a.get("network", "")))
    now = int(time.time())    nonce = secrets.token_bytes(32)    types = {"TransferWithAuthorization": [        {"name": "from", "type": "address"}, {"name": "to", "type": "address"},        {"name": "value", "type": "uint256"}, {"name": "validAfter", "type": "uint256"},        {"name": "validBefore", "type": "uint256"}, {"name": "nonce", "type": "bytes32"},    ]}    domain = {"name": "USD Coin", "version": "2", "chainId": 8453, "verifyingContract": accepted["asset"]}    msg = {"from": account.address, "to": accepted["payTo"], "value": int(accepted["amount"]), "validAfter": 0, "validBefore": now + 300, "nonce": nonce}    sig = account.sign_message(encode_typed_data(domain_data=domain, message_types=types, message_data=msg)).signature.hex()
    payment_b64 = base64.b64encode(json.dumps({        "x402Version": 2, "resource": pr_json.get("resource"), "accepted": accepted,        "payload": {"signature": "0x" + sig.lstrip("0x"), "authorization": {            "from": account.address, "to": accepted["payTo"], "value": str(accepted["amount"]),            "validAfter": "0", "validBefore": str(now + 300), "nonce": "0x" + nonce.hex()        }}    }).encode()).decode()
    # 3. Settle & unlock premium response    paid_res = requests.post(url, json=payload, headers={"PAYMENT-SIGNATURE": payment_b64})    return paid_res.json()

🚀 Connecting to the Hosted Endpoint

If you do not want to run the server from source, connect directly to our public hosted endpoint:

  • Remote MCP URL: https://x402-agent-tollbooth.onrender.com/mcp
  • Discovery Manifest: https://x402-agent-tollbooth.onrender.com/.well-known/mcp/server-card.json
  • x402 Manifest: https://x402-agent-tollbooth.onrender.com/.well-known/x402.json
  • Smithery CLI Install:
bash
npx @smithery/cli mcp install x402-agent-tollbooth

Source: README.md at commit e6a12a5

Tools

4

ai_intel

Deep AI Vulnerability & Intelligence Engine. Scans contracts and code for logic vulnerabilities and exploits on Base. Cost: 0.001 USDC on Base & Solana (100% gasless).

ParameterspromptcontractAddress

arbitrage_scan

Cross-DEX Arbitrage & Liquidity Scanner. Analyzes Uniswap, Aerodrome, and BaseSwap pools for profitable routing opportunities. Cost: 0.002 USDC on Base & Solana (100% gasless).

Parameterspairmin_spread_bps

smart_router

Optimal Execution Smart Router. Computes optimal gas and slippage routing paths for Base AI agents and automated executors. Cost: 0.001 USDC on Base & Solana (100% gasless).

ParametersamounttokenIntokenOut

contract_audit

Live Smart Contract AI Auditor. Analyzes Base contracts for vulnerabilities. Cost: 0.02 USDC via x402 protocol. Cost: 0.02 USDC on Base & Solana (100% gasless).

ParametersisPatchcontractAddress

Version history

1
  1. v2.1.0LatestOct 15, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts