Non-custodial USDT and USDC payments from your AI assistant: invoices, payment totals and ready prompts across your Stablevoy stores, docs without a key. Keys cannot move funds.
XPayr Non-Custodial Crypto Gateway & AI Agent Commerce is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
21 MCP tools for non-custodial crypto checkout, USDT/USDC links, webhooks, and AI agents.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user xpayr-non-custodial-crypto-gateway-ai-agent-c-mcp '--' npx -y --package=@xpayr/mcp-server xpayr-mcp
# 2 — ask your agent for something these tools do
# xpayr_health_check, xpayr_create_payment_session, xpayr_get_payment_session and 18 more
XPayr Non-Custodial Crypto Gateway & AI Agent Commerce costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts XPayr Non-Custodial Crypto Gateway & AI Agent Commerce as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user xpayr-non-custodial-crypto-gateway-ai-agent-c-mcp '--' npx -y --package=@xpayr/mcp-server xpayr-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take XPAYR_API_KEY (XPayr Merchant Secret Key (sk_test_... or sk_live_...) from https://xpayr.com/merchant/register (optional for public/offline tools).) if you want to set it.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
21 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Check XPayr Gateway API v1 operational health, version, and server timestamp (public endpoint, no API key required).
No parameter schema on file.
Create a non-custodial crypto payment session supporting Dual Checkout (Web3 1-Click Pay & Direct Transfer / QR from Binance/Bybit/OKX with on-chain explorer verification), multi-chain agnostic links, 1-year reusable payment links, and automated HTML invoice email delivery.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount | number | yes | Invoice amount in fiat/token units (e.g., 49.90). |
| currency | string | yes | Payment token symbol (e.g., USDT, USDC, SOL, TRX, BNB, ETH, MATIC). |
| network | string | no | Blockchain network key (e.g., tron-mainnet, bsc-mainnet, solana-mainnet, polygon-mainnet, base-mainnet, arc-mainnet, bsc-testnet). Optional if is_multi_chain is true. |
| order_id | string | no | Merchant internal order or invoice reference ID (e.g., ORD-1001). |
| description | string | no | Human-readable order description shown on checkout and invoice. |
| is_multi_chain | boolean | no | When true, generates a universal multi-chain link allowing the buyer to dynamically choose their network and token at checkout. |
| is_reusable | boolean | no | When true, the payment link remains active for 1 year and accepts repeated payments. |
| send_invoice_email | boolean | no | When true and customer_email is provided, sends a branded responsive HTML invoice email with 1-click payment CTA. |
| customer_email | string | no | Buyer email address for invoice delivery and payment receipt notifications. |
| coupon_code | string | no | Optional promotional discount coupon code to apply. |
| success_url | string | no | HTTPS redirect URL after confirmed payment. |
| cancel_url | string | no | HTTPS redirect URL if customer cancels checkout. |
| ipn_callback_url | string | no | HTTPS webhook endpoint URL for HMAC-SHA256 signed payment lifecycle events. |
Retrieve full details, metadata, settlement split amounts, checkout mode, and on-chain transaction hash for a specific XPayr payment session.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | Payment session ID (e.g., ps_6b5b7d8737c0e0ec0a04a29a045d2d5d). |
List merchant crypto payment sessions with optional filtering by status (pending, completed, expired, failed), currency, network, and pagination.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Filter by session status (pending, processing, completed, expired, failed). |
| currency | string | no | Filter by token symbol (e.g., USDT, USDC). |
| network | string | no | Filter by blockchain network key (e.g., tron-mainnet, solana-mainnet). |
| limit | integer | no | Number of sessions to return per page (1-100). |
Poll real-time public checkout status, on-chain tx_hash, sender wallet address, block confirmations, and paid_at timestamp for any session (public endpoint, no API key required).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | Payment session ID (e.g., ps_6b5b7d8737c0e0ec0a04a29a045d2d5d). |
Validate and apply a merchant discount coupon code to an active pending payment session and recalculate the effective crypto price.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | Target payment session ID. |
| coupon_code | string | yes | Discount coupon code to apply. |
Retrieve authenticated merchant profile, business name, primary settlement wallet address, commission rate in basis points (50 bps = 0.5%), active API keys, and livemode status.
No parameter schema on file.
Query confirmed non-custodial settlement volume, transaction counts, total merchant received amounts, and platform fees grouped by currency and blockchain network.
No parameter schema on file.
List all active EVM, TRON, Solana, and Arc Mainnet/Testnet blockchain networks, chain IDs, RPC endpoints, smart-contract splitters, and supported tokens enabled for the current API key mode.
No parameter schema on file.
Inspect the merchant webhook callback URL, masked HMAC-SHA256 signing secret, and subscribed payment lifecycle events (payment.pending, payment.completed, payment.failed, payment.expired).
No parameter schema on file.
Configure or update the merchant HTTPS webhook receiver URL and generate a fresh 32-byte HMAC-SHA256 signing secret.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | HTTPS webhook endpoint URL (e.g., https://mystore.com/webhooks/xpayr). |
Dispatch a signed test.webhook event with HMAC-SHA256 headers to the configured merchant webhook URL to verify signature validation and delivery.
No parameter schema on file.
Provision a new merchant-managed AI commerce agent identity with scoped credentials and programmable spending guardrails.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Human-readable AI agent name (e.g., Procurement Bot Alpha). |
| description | string | no | Purpose and operational scope of the AI agent. |
| wallet_address | string | no | Optional agent execution wallet address. |
List all AI commerce agents managed by the merchant along with their status, assigned wallets, and spending policies.
No parameter schema on file.
Upsert spending policy rules for an AI commerce agent, including maximum per-transaction USD amount, daily budget cap, auto-approve threshold, and allowed blockchain networks/tokens.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | Public ID of the target AI agent. |
| max_tx_amount | number | no | Maximum allowed single transaction amount in USD. |
| daily_limit_amount | number | no | Maximum daily cumulative spend in USD. |
| auto_approve_under | number | no | Transactions below this USD amount are auto-approved; higher amounts enter the human approval queue. |
| allowed_networks | array | no | List of permitted blockchain network keys. |
| allowed_currencies | array | no | List of permitted token symbols (e.g., ["USDC", "USDT"]). |
Submit an autonomous AI agent payment intent evaluated in real time against merchant spending policy guardrails (returns approved, pending_approval, or rejected).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount | number | yes | Requested payment amount (e.g., 25.00). |
| currency | string | yes | Requested token symbol (e.g., USDC, USDT). |
| network | string | no | Target network key (e.g., arc-testnet, base-mainnet, solana-mainnet). |
| recipient_address | string | no | Destination wallet or merchant settlement address. |
| reason | string | no | Justification or invoice memo for the AI agent payment. |
| external_reference | string | no | External task, tool, or invoice correlation ID. |
List AI agent payment intents, policy evaluation decisions, and audit trail records for the merchant.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Filter by decision status (approved, pending_approval, rejected, bridged). |
| limit | integer | no | Maximum records to return. |
Bridge an approved AI agent payment intent into a live executable XPayr payment session with hosted checkout URL and on-chain verification.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| intent_id | string | yes | Approved agent payment intent ID. |
Approve a pending AI agent payment intent from the merchant human-in-the-loop approval queue and optionally bridge it to a checkout session.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| intent_id | string | yes | Pending agent intent ID to approve. |
| note | string | no | Optional reviewer approval note. |
Reject a pending AI agent payment intent in the merchant approval queue with an audit reason.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| intent_id | string | yes | Pending agent intent ID to reject. |
| reason | string | no | Reviewer rejection reason. |
Deterministically calculate XPayr flat 0.5% (50 bps) gateway fee split, net merchant wallet settlement, exchange withdrawal underpayment tolerance (1%, max $0.50), and cost savings compared to BitPay (1%), Coinbase Commerce (1%), NOWPayments (0.5%-1%), and Stripe (2.9% + $0.30). Works offline…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount | number | no | Transaction or monthly volume amount in USD/USDT (e.g., 1000.00). |
| currency | string | no | Settlement token symbol (e.g., USDT, USDC). |
| network | string | no | Blockchain network (e.g., tron-mainnet, solana-mainnet, bsc-mainnet, base-mainnet, arc-mainnet). |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install XPayr Non-Custodial Crypto Gateway & AI Agent Commerce or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (21 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| xpayr_health_check | no tags | |
| xpayr_create_payment_session | no tags | |
| xpayr_get_payment_session | no tags | |
| xpayr_list_payment_sessions | no tags | |
| xpayr_get_public_payment_status | no tags | |
| xpayr_apply_payment_coupon | no tags | |
| xpayr_get_merchant_profile | no tags | |
| xpayr_get_merchant_balance | no tags | |
| xpayr_get_supported_networks | no tags | |
| xpayr_get_webhook_config | no tags | |
| xpayr_set_webhook_endpoint | external-sink | external-sink: keyword "webhook" |
| xpayr_send_test_webhook | external-sink | external-sink: keyword "webhook" |
| xpayr_create_ai_agent | no tags | |
| xpayr_list_ai_agents | no tags | |
| xpayr_update_ai_agent_policy | no tags | |
| xpayr_submit_agent_payment_intent | external-sink | external-sink: parameter "recipient" |
| xpayr_list_agent_payment_intents | no tags | |
| xpayr_bridge_agent_intent_to_checkout | no tags | |
| xpayr_approve_agent_intent | no tags | |
| xpayr_reject_agent_intent | no tags | |
| xpayr_calculate_gateway_fee_and_split | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.0.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish XPayr Non-Custodial Crypto Gateway & AI Agent Commerce can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.