All MCP server API requests have a 30-second timeout and all user-supplied parameters are
sanitized before URL interpolation to prevent path injection.
Payments (6)
pay
Request and execute a payment in one step. Combinesrequest_payment + execute_payment. Fails if the payment is denied or requires manual approval.
Parameters:
request_payment
Request authorization for a payment. Evaluates spending policies and returns whether the payment is approved, denied, or requires manual approval. Parameters: Same aspay.
Returns: requestId, status (APPROVED / DENIED / REQUIRES_APPROVAL), wallet, reasons, and violations.
execute_payment
Execute a previously approved payment request. Execution is not automatically retried. After a timeout or ambiguous failure, callcheck_payment_status with the same requestId before deciding whether another execution attempt
is safe.
approve_external_payment
Request approval for a payment from an external (agent-held) wallet.confirm_external_payment
Confirm an externally-executed payment was completed onchain.Wallets & Limits (3)
get_wallet
Budget Requests (2)
request_budget
Request a spending budget for payments. Submits a request for human approval. Only one active budget request per agent at a time. Applies to all payment types (standard, x402, MPP).get_budget_request
Check status and remaining balance of your budget requests. Use to poll for approval after submitting a request, and to monitor remaining budget during spending.Transactions (3)
list_transactions returns paginated customer transaction records with related resource IDs,
lifecycle timestamps, authorization decisions, and network receipt data. get_transaction adds
source-wallet and recipient identities plus customer-visible linked alerts, so an agent can explain
and reconcile a payment without relying on provider or database fields.
retry_transaction requires transactionId and the transactions:write admin scope. A successful
response includes the transaction ID, current status, and statusUrl; inspect that URL after an
ambiguous client result. Only eligible failed transactions can be retried, so confirm with the user
before calling this non-idempotent tool.
list_transactions
Connected Cards (1)
Connected cards are customer cards enrolled through the provider and delegated to this agent. This is a gated pilot: the tool returns not-found until the tenant is enabled.
connected_card_list is read-only (transactions:read) and returns masked cards only. Each card exposes last4, brand, funding type, spending limits, and its active mandates. No card number, security value, or provider token is ever returned.
There is deliberately no connected_card_draw MCP tool. A draw returns live single-use card material once, and an MCP tool result enters the model transcript and is commonly logged by the host. Drawing a credential is a programmatic SDK operation (conto.connectedCards.draw), not an LLM-tool operation. A draw tool is deferred pending a separate decision on agentic-checkout execution.
connected_card_list
Takes no parameters.x402 Protocol (4)
x402_pre_authorize
serviceDomain is derived automatically from resourceUrl.
This is a read-only policy and budget evaluation. It does not reserve funds or record spend.
x402_record
Provide
payerAddress and network together on both calls. They are required when the agent has
more than one active wallet.
x402_get_budget
Pass an optionalsessionId to include spend for that customer-defined session alongside the
aggregate daily, weekly, and monthly totals.
x402_list_services
MPP Protocol (4)
mpp_pre_authorize
This is a read-only policy and budget evaluation. It does not reserve funds or record spend.
mpp_record
MPP recording rejects an unsuccessful receipt, a receipt bound to a different challenge, or a
settled amount that does not match
amount. Receipt parsing is only a consistency check because
the payload is caller supplied; a receipt-only record remains pending. An on-chain transaction is
marked confirmed only after its sender, recipient, amount, and currency match the record.
mpp_get_budget
Pass an optionalsessionId to include spend for that customer-defined session alongside the
aggregate daily, weekly, and monthly totals.
Agent-to-Agent (6)
a2a_send_request
a2a_respond
Trust & Intelligence (4)
create_counterparty
Monitoring (4)
list_alerts
get_alert
respond_to_alert
Safety and reconciliation alerts — automatic agent freezes, protection-check failures, and
payments flagged for manual reconciliation — are read-only to an agent.
respond_to_alert returns
a 403 for these, and they must be acknowledged or resolved by a human in the dashboard.
list_alerts and get_alert still return them.Analytics & Info (7)
request_policy_exception
Use this when a payment is blocked and the customer wants to request a counterparty, spending-limit, time-window, category, or custom policy change. The API key must include thepolicies:exceptions scope.
The response includes the request reference, normalized type and priority, current review status,
timestamps, and a dashboard review URL.
list_policy_exceptions
List policy change requests with customer-readable statuses and pagination. The API key must include thepolicies:exceptions scope.
get_all
get_all is retained for compatibility with existing MCP integrations. New integrations should
use get_setup and the dedicated list tools.
Use the optional include parameter to request only the sections you need. A section is returned
only when the API key has its corresponding read scope; omittedSections identifies sections that
could not be returned and the scope each one requires.