Niches · Spend management & procurement

Issue a card with limits for a person, vendor or agent

One company's docs show a full fit.

1companies, full fit
5companies, fit with a limit
7companies carry the tag
12share of the category's work
3first-hand accounts

What counts as done

A virtual card or spend limit created once with the amount, period and locks set and readable back, the card number shown to the holder through the vendor's secure display rather than returned to the agent, and the change recorded in the audit log.

How agents ask for it: make a virtual card for our OpenAI bill with a 500 dollar limit, give the new hire a card, lock the card used for this subscription, raise the travel budget for Sam

Does the job 1

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Ramp C
Ramp Business Corporation
POST /funds takes X-Idempotency-Key and spending_restrictions (limit, interval, transaction_amount_limit, lock_date, allowed or blocked categories, MCCs and vendors), funds read back by id, and an embed init token shows the card to the holder; the audit log records changes on Plus. source

Does the job, with a limit 5

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Airwallex Spend and Issuing B
Airwallex US, LLC
Issuing creates cards with single-use or multi-use, transaction limits by amount and interval, allowed currencies, MCCs and blocked scopes, using request_id, and secure iframes show the number to the holder. The Security Audit Logs cover logins and user and key changes, not API calls (context note). source
BILL B
Bill.com, LLC
POST /v3/spend/cards creates a vendor card, budgets set limits and members, and freeze and unfreeze exist. GET pan-jwt hands the caller a 5-minute token that decodes to the full number, which acc-11 used through BILL's embed; no idempotency key on create. source
Brex B
Brex LLC
POST /v2/cards with spend_controls and POST /v2/spend_limits create cards and limits, lock and unlock exist, and an Idempotency-Key is required on card create (context note). GET /v2/cards/{id}/pan returns the number, CVV and expiry to the caller; the secure-email route is gated. source
Mercury API B
Mercury Technologies, Inc.
POST create card makes virtual cards with spendLimit, interval, merchantLock, categoryLocks and singleUse, read back by id. No idempotency key was found, cardholders must exist first, and reveal-PAN returns the full number to the caller for agent cards; acc-07 found card creation missing from the CLI. source
Payhawk API + MCP C
Payhawk Limited
POST cards issues a card to a registered user with daily and single-transaction limits, refill schedules, merchant category rules and country limits, and no card number field appears in the API. No idempotency on card issue was found. source

Doesn't do this job 3

Listings in the category that do something else, with the reason.

ListingWhy
Expensify F
Expensify, Inc.
Card data appears in reconciliation exports and card-owner data only; no card or limit creation. source
Pleo API + MCP B
Pleo Technologies A/S
No card or spend-limit endpoint in the API index, and the MCP focuses on processing expenses. source
Spendesk API + MCP B
Spendesk SAS
Cards are read-only (list, get, blocking history, order); no create, limit or lock call. source

What stops agents finishing

  • card issuing not available through the MCP or CLI
  • direct payment sends need an allowlisted IP

Around it

Before: spend-management.approve-requests. After: payment-platforms.pay-vendor, agent-wallets.fund-agent.

Where this comes from

Weight 12 of 100 in Spend management & procurement: 3 of 18 accounts (acc-07, acc-11, acc-15); two want cards with hard limits for automated or agent spending

The same as data: /api/v1/use-cases/spend-management.issue-card.json, or the MCP tool get_use_case with id spend-management.issue-card. Other jobs in this category: /api/v1/niches?category=spend-management.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

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.