agentpay — card-funded wallets for AI agents

Pay a service

pay_service

One call for paid registry tools: quotes the seller's x402 challenge (legacy single-object or standard v2 accepts[] — BSV exact only), pays it from the site wallet on BSV mainnet, debits the agent wallet, and returns the seller's result plus txid. If the seller rejects the payment, the debit is refunded. For pay-per-call LLM with no API key, use chat; for typed values from messy text or receipts, use extract. Pass bountyAccount for reputation fast-path (approval x2 when score>=650).

Input Schema

Name	Required	Description
`key`	No	Agent key (agp_…). Optional when the MCP connection sends Authorization: Bearer.
`ref`	No
`tool`	Yes	Tool name on that service
`dryRun`	No	Sandbox: quote + policy check only, no debit or settlement
`params`	No	Tool arguments (body for POST, query for GET)
`serviceId`	Yes	Registry service id (from list_services)
`approvalId`	No	Approval id from a prior approval_required response
`amountCents`	No	Override the USD cents charged (min 1 cent default)
`description`	No
`bountyAccount`	No	BSVBounties account # for trust fast-path

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 11, 2026

addedInput schema / properties / bountyAccount

Added value: +{
+  "description": "BSVBounties account # for trust fast-path",
+  "exclusiveMinimum": 0,
+  "maximum": 9007199254740991,
+  "type": "integer"
+}

addedInput schema / properties / dryRun

Added value: +{
+  "description": "Sandbox: quote + policy check only, no debit or settlement",
+  "type": "boolean"
+}

First observedSep 10, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and largely meets it: it discloses real side effects (pays from the site wallet on BSV mainnet, debits the agent wallet) and failure semantics ('If the seller rejects the payment, the debit is refunded'), plus the return shape. It omits idempotency/retry and double-charge behavior, which matters for a money-moving tool.

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 primary action and effect, then routing guidance. The parenthetical challenge-format aside ('legacy single-object or standard v2 accepts[] — BSV exact only') is dense technical detail but defensible for a payment tool. Overall tight with little waste.

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

Completeness4/5

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

For a complex, 10-parameter, nested-object payment tool with no annotations and no output schema, the description covers the action chain, failure/refund behavior, and return content (result + txid). The approval_required flow referenced by approvalId is only implied, which is the main remaining gap.

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

Parameters3/5

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

Schema description coverage is high (~80%), so the schema already documents most parameters and a 3 is the baseline. The description adds genuine meaning for bountyAccount ('reputation fast-path — approval x2 when score>=650') that the schema does not, but leaves the other nine parameters (key, ref, tool, dryRun, params, approvalId, amountCents) to the schema.

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?

States a specific verb+resource (pay a paid registry tool via x402 challenge) and enumerates the full action chain: quote, pay from site wallet on BSV mainnet, debit agent wallet, return result plus txid. It explicitly distinguishes itself from named siblings chat and extract, so an agent can route without opening another schema.

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

Usage Guidelines4/5

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

Explicitly names alternatives with their selecting conditions: 'For pay-per-call LLM with no API key, use chat; for typed values from messy text or receipts, use extract.' It also gives a usage rule for bountyAccount. It stops short of the natural adjacent alternative service_quote/dryRun for quote-only lookups, so it is clear but not exhaustive.

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

All agentpay — card-funded wallets for AI agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?