Get an audit

Head to head · Spend transactions · October 2026 research run

Airwallex Spend and Issuing vs Mercury API

Airwallex Spend and Issuing scores 68.3 (B) on agent readiness against Mercury API's 63.8 (B), and leads in 5 of 7 scored categories. Mercury API leads on payments & pricing. Both do spend transactions.

Airwallex Spend and IssuingAirwallex · HTTP API B68.3/100#187 of 722 Mercury APIMercury Technologies, Inc. · HTTP API B63.8/100#293 of 722

Which one, for what

Airwallex Spend and Issuing B

Good for A company already banking with Airwallex in several currencies that wants an agent to issue cards with limits, read card transactions and expenses, load vendors, purchase orders and bills, and sync status to an ERP.

Ahead on

  • Reliability, 77 against 59
  • Transparency & trust, 78 against 63

Watch for

No OpenAPI spec was found. The reference is a Markdown page per endpoint, and the CLI prints one endpoint's schema at a time

Mercury API B

Good for A company that banks with Mercury and wants an agent to read balances and transactions, set notes and categories, upload receipts, issue virtual cards with spend limits and queue payments for human approval.

Ahead on

  • Payments & pricing, 30 against 25

Watch for

No rate limits with numbers and no 429 handling were found in the reviewed documentation

Score by category

CategoryWeight this runAirwallex Spend and IssuingMercury APIEdge
Reliability16%207759Airwallex Spend and Issuing +18
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26972Mercury API +3
Agent ergonomics13%16.26968Airwallex Spend and Issuing +1
Security & auth14%17.58482Airwallex Spend and Issuing +2
Payments & pricing10%12.52530Mercury API +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86664Airwallex Spend and Issuing +2
Transparency & trust7%8.87863Airwallex Spend and Issuing +15
Negative events≤1500
Total68.3 · B63.8 · B

Facts side by side

FactAirwallex Spend and IssuingMercury API
KindHTTP APIHTTP API
VendorAirwallexMercury Technologies, Inc.
Hosted endpointhttps://api.airwallex.comhttps://api.mercury.com/api/v1
TransportsHTTPHTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceProprietary service under Airwallex's service agreement and API terms. The plugin and skills repository is Apache-2.0 and @airwallex/node-sdk is MITProprietary service under Mercury's Terms of Use. The Mercury CLI on GitHub is Apache-2.0
Tools exposednone35
Read-only variant documentednoyes
llms.txtyesyes
Last release2026-09-302026-08-12
Terms last updated2025-06-20no date given
Privacy policy last updatedno date givenno date given
Customer content may train modelsyesnot found in the text
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity7 stars, 44k npm/wknone

Verdicts

Airwallex Spend and Issuing

Scoped API keys split read from write per resource, tokens last 30 minutes, and the sandbox opens at once with no contract. No OpenAPI spec was found, every Spend endpoint read is marked beta, the pricing page lists direct Spend API integration under the custom-priced Accelerate plan, and no SLA was found.

Mercury API

Custom tokens take per-endpoint scopes, write tokens need an IP allowlist, and payments can be queued for approval in the dashboard through POST /account/{accountId}/request-send-money. No rate limits, error catalogue or SLA were found in the reviewed documentation, the changelog carries no dates, and the MCP server is beta.

Before you call either

Airwallex Spend and Issuing

  1. Exchange x-client-id and x-api-key at POST /api/v1/authentication/login once, then reuse the bearer token for 30 minutes. The login endpoint allows 100 requests a minute per key
  2. Create Spend keys with organisation-level permissions. With a key linked to several accounts, send x-login-as at login or the token carries no account permissions
  3. Send a fresh UUID as request_id on every create call and reuse the same value when retrying after a timeout
  4. Expect two pagination styles. Spend and card transaction events use the page bookmark with page_after and page_before. Cards and legacy transactions use page_num and has_more
  5. Card and expense lists default to the last 30 days. Pass both created-at bounds to read further back, and fetch a card singly to see its authorization_controls

Mercury API

  1. Ask for a Custom token with only the scopes the task needs. Scopes can't be edited later, and a token unused for 45 days is deleted.
  2. Without a fixed IP address, send payments through POST /account/{accountId}/request-send-money. Direct sends through POST /account/{accountId}/transactions need an allowlisted IP.
  3. Send a stored idempotencyKey with every payment. The same recipient, account, amount and method within 24 hours returns 400 even with a new key.
  4. Set limit on list calls. GET /transactions returns up to 1,000 rows by default.
  5. Test against https://api-sandbox.mercury.com/api/v1/ with a sandbox token. Webhooks aren't available in the sandbox.

Questions

Which is better for AI agents, Airwallex Spend and Issuing or Mercury API?

Airwallex Spend and Issuing scores 68.3 (B) on agent readiness against Mercury API's 63.8 (B), and leads in 5 of 7 scored categories. Mercury API leads on payments & pricing.

Do Airwallex Spend and Issuing and Mercury API need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call Airwallex Spend and Issuing and Mercury API without installing anything?

Yes. Airwallex Spend and Issuing has a hosted endpoint at https://api.airwallex.com and Mercury API at https://api.mercury.com/api/v1.

Other comparisons with Airwallex Spend and Issuing or Mercury API

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report