Skip to main content
Glama

Quantum Atlas Stripe X402 Agent Payment Hub

Create Stripe Credit Checkout

x402_create_checkout

Create a hosted Stripe Checkout session ($10, $25, $100, $250, or $500 prepaid USD credit pack via card, Apple Pay, Google Pay, or Link — zero crypto required) to fund a new or existing master spend key. Use this when provisioning a brand-new account or topping up a low balance reported by x402_get_account or x402_quote_plan; do not use this to check balances (use x402_get_account) or mint child keys (use x402_issue_delegate_key). Opens an external Stripe Checkout URL without charging until a human completes payment. Omit spend_key to create a new master account, or pass a master sbk_* key to top up; delegated subagent keys are rejected with HTTP 403.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "amount_cents": "<amount_cents>"
    },
    "name": "x402_create_checkout"
  }
}

Input Schema

NameRequiredDescriptionDefault
spend_keyNoMaster Stripe account spend key (format: sbk_<43+ chars>). Delegated subagent keys are rejected with HTTP 403. Optional if supplied via the x-atlas-spend-key HTTP header.
amount_centsYesPrepaid Stripe credit pack size in USD cents: 1000 ($10), 2500 ($25), 10000 ($100), 25000 ($250), or 50000 ($500).
return_surfaceNoWeb console surface to redirect the operator to after Stripe Checkout finishes: "x402" (default, quantumatlas.xyz/x402/), "developers", or "app".

Output Schema

NameRequiredDescriptionDefault
okYesTrue when the Stripe Checkout session was created.
spend_keyNoNewly generated master sbk_* key (returned only when creating a brand-new account).
account_idNoMaster account identifier that will receive the credit pack.
amount_usdNoFormatted USD amount of the selected credit pack.
checkout_urlNoHosted Stripe Checkout URL for the human operator to complete payment.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare openWorld, non-readOnly, non-idempotent, non-destructive, so the description adds the context that matters: an external Stripe Checkout URL is opened and no charge occurs until a human completes payment, plus a delegated key is rejected with HTTP 403. What it omits is the practical consequence of idempotentHint=false and openWorldHint=true — that repeated calls spawn separate sessions and that sessions can expire — which would round out the payment lifecycle.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action before any qualification, then usage, then behavior — a sensible order for a tool an agent might call blind. Slight waste: the balance-check exclusion appears twice in one paragraph ("topping up a low balance reported by x402_get_account" and "do not use this to check balances (use x402_get_account)"), and the parenthetical denylist of payment methods is longer than the routing decision requires.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a payment-initiation tool with three parameters, one required, this covers everything an agent needs to call correctly: allowed amounts, the header alternative for spend_key, key-type rejection, redirect surface behavior, and no-charge-until-human-completes. An output schema exists, so the absence of return-value description is appropriate rather than a gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns above that by disclosing a semantic the schema does not state: omitting spend_key creates a new master account rather than erroring, while passing one tops up an existing account. It also restates the rejected-delegate rule, which is mildly redundant with the spend_key property description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource ("Create a hosted Stripe Checkout session") and pins the scope precisely: the five fixed USD credit-pack amounts, funding a master spend key, payment rails accepted, and no crypto. An agent can distinguish it from x402_get_account or x402_issue_delegate_key without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit positive trigger (provisioning a brand-new account or topping up a low balance reported by x402_get_account/x402_quote_plan) and two explicit exclusions that name the correct sibling for each (balances → x402_get_account, child keys → x402_issue_delegate_key). Nothing about routing is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources