Get an audit

Head to head · Spend transactions · October 2026 research run

Mercury API vs Spendesk API + MCP

Mercury API scores 63.8 (B) on agent readiness against Spendesk API + MCP's 62.3 (B), and leads in 4 of 7 scored categories. Spendesk API + MCP leads on schema & documentation and transparency & trust. Both do spend transactions.

Mercury APIMercury Technologies, Inc. · HTTP API B63.8/100#293 of 722 Spendesk API + MCPSpendesk SAS · HTTP API B62.3/100#342 of 722

Which one, for what

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

  • Agent ergonomics, 68 against 62
  • Payments & pricing, 30 against 0
  • Maintenance & community, 64 against 57

Watch for

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

Spendesk API + MCP B

Good for A finance team already on Spendesk that wants an assistant to analyse spend, follow invoices and prepare the accounting close, or an ERP sync reading payables and settlements.

Ahead on

  • Schema & documentation, 87 against 72
  • Transparency & trust, 80 against 63

Watch for

No public price, free tier or self-serve signup. API access and demo credentials are requested from a Spendesk representative

Score by category

CategoryWeight this runMercury APISpendesk API + MCPEdge
Reliability16%205955Mercury API +4
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27287Spendesk API + MCP +15
Agent ergonomics13%16.26862Mercury API +6
Security & auth14%17.58286Spendesk API + MCP +4
Payments & pricing10%12.5300Mercury API +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86457Mercury API +7
Transparency & trust7%8.86380Spendesk API + MCP +17
Negative events≤1500
Total63.8 · B62.3 · B

Facts side by side

FactMercury APISpendesk API + MCP
KindHTTP APIHTTP API
VendorMercury Technologies, Inc.Spendesk SAS
Hosted endpointhttps://api.mercury.com/api/v1https://public-api.spendesk.com
TransportsHTTPHTTP
AuthOAuth or keyOAuth or key
PricingFreemiumPaid
x402nono
LicenceProprietary service under Mercury's Terms of Use. The Mercury CLI on GitHub is Apache-2.0Proprietary service under Spendesk's terms and conditions and a separate Spendesk API agreement
Tools exposed3562
Read-only variant documentedyesno
llms.txtyesyes
Last release2026-08-122026-09-29
Terms last updatedno date givencouldn't be read
Privacy policy last updatedno date given2025-03-01
Customer content may train modelsnot found in the textcouldn't be read
Terms restrict automated accessyescouldn't be read
Terms restrict benchmarkingyescouldn't be read
Terms or service can change without noticenot found in the textcouldn't be read
Arbitration or class-action waiveryescouldn't be read

Verdicts

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.

Spendesk API + MCP

Scoped credentials, MCP write permissions that are off by default, an action log and published guidance on prompt injection suit delegated finance work. Access needs a paying customer and a request to Spendesk, most write endpoints are experimental, no official SDK was found, and the status page lists three critical incidents between 2 and 29 September 2026.

Before you call either

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.

Spendesk API + MCP

  1. Request a token at POST /v1/auth/token with HTTP Basic (client ID and secret). It lasts 3,600 seconds, so renew on a 401
  2. Stop paging at the last page calculated from total and pageSize (maximum 30). A page past the end returns 404, not an empty list
  3. With an organisation-level token, send X-Company-Id on every v1 call or expect a 400
  4. The MCP server refuses API keys. Connect with OAuth authorisation code and PKCE, and treat Tool not found (-32601) as a missing permission
  5. After an unclear write result, read the object again before retrying. Creating a purchase order or supplier twice creates two

Questions

Which is better for AI agents, Mercury API or Spendesk API + MCP?

Mercury API scores 63.8 (B) on agent readiness against Spendesk API + MCP's 62.3 (B), and leads in 4 of 7 scored categories. Spendesk API + MCP leads on schema & documentation and transparency & trust.

Do Mercury API and Spendesk API + MCP need an API key?

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

Can an agent call Mercury API and Spendesk API + MCP without installing anything?

Yes. Mercury API has a hosted endpoint at https://api.mercury.com/api/v1 and Spendesk API + MCP at https://public-api.spendesk.com.

Other comparisons with Mercury API or Spendesk API + MCP

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