HPSILab x402 Pay-Per-Call for AI Agents
Stop managing API keys and pre-paid credit balances for quant-finance tools.
$9
Works with the AI Agents you already use
HPSILab x402 Pay-Per-Call for AI Agents
Example session with this skill installed
Show me how to set up a capped payment policy for the get_monte_carlo tool that limits spending to $0.20 per call and $5.00 per day.
- Read your context and instructions
- Compiled the hpsilab x402 pay-per-call
I have configured the HPSILab x402 payment policy with your specified constraints. This setup ensures the agent can only pay for Monte Carlo simulations within the defined budget, using local signing to keep your private key secure.
x402 Payment Policy Configuration
from hpsilab_mcp import HpsiMcpClient, X402Wallet, PaymentPolicy
# Initialize wallet with a safety cap for a single signature
wallet = X402Wallet(max_price_usdc=0.20)
# Define strict spending limits and tool allowlist
policy = PaymentPolicy(
mode="x402_fallback",
max_payment_per_call=0.20,
max_payment_per_session=1.00,
max_payment_per_day=5.00,
allowed_payment_assets={"USDC"},
allowed_networks={"base"},
x402_allowed_tools={"get_monte_carlo"}
)
# Instantiate client - will only pay if HTTP 402 is received
client = HpsiMcpClient(wallet=wallet, payment_policy=policy)
# Example usage
try:
result = client.get_monte_carlo("TSLA")
print(f"Spend summary: {client.payment_spend_summary()}")
except Exception as e:
print(f"Call failed: {e}")
Next steps
- Ensure
HPSILAB_X402_PRIVATE_KEYis set in your environment variables. - Fund your Base wallet with a small amount of USDC to act as a float.
- Verify the current price of the
get_monte_carlotool via the HPSILab credits catalog.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop managing API keys and pre-paid credit balances for quant-finance tools. This skill implements the x402 protocol to enable pay-per-call access to HPSILab stock and options research, letting your agents pay for individual requests in USDC on the Base network.
What it does
- Automates 402 recovery by detecting HTTP 402 Payment Required responses and signing challenges to retry requests.
- Enforces spending caps with granular controls for per-call, per-session, and per-day limits in USD.
- Secures private keys using local signing that keeps EVM private keys in the environment and out of logs or chat history.
- Restricts tool access through a configurable allowlist to prevent agents from paying for unintended API calls.
- Manages settlement risk by identifying unknown settlement states to prevent double-spending on retries.
How it works
- Initialize the wallet by loading an EVM private key from the environment and setting a maximum price guard.
- Define a payment policy specifying the allowed assets, networks, spending limits, and tool allowlist.
- Configure the client with the wallet and policy to enable the
x402_fallbackmode. - Execute research calls like Monte Carlo simulations or pre-trade risk scans which automatically pay only when quotas are exhausted.
Frameworks & tools
This skill uses the hpsilab-mcp Python SDK with the x402 extra for local signing. It operates on the Base blockchain using USDC.
Why this beats prompting it yourself
Manual prompting often fails to handle the complex state of a 402 challenge or risks leaking sensitive private keys in the chat context. This skill provides the specific error handling logic required to prevent catastrophic retry loops that could drain a wallet.
Use cases
- Anonymous research accessing Pro-tier quant data without creating an account or managing HPSILab credits.
- Autonomous agents that need to self-fund their own data requirements for stock predictions or IV radar.
- CI/CD pipelines that run occasional backtests without needing a permanent subscription.
Known limitations
A funded wallet does not top up an existing HPSILab account. It only works for anonymous callers without an API key. Settlement unknown errors require manual reconciliation and stop the payment path.
Works only for anonymous calls without an API key. Requires a funded EVM wallet on Base with USDC. Settlement unknown errors require manual reset of the payment path.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 10 days ago
Requires