Category · Domain data
Spend management and procurement platforms for AI agents
Company cards, expenses, bills and purchasing, with an interface an agent can use to read transactions, match receipts, code expenses and raise purchase requests. Compared on API coverage, write access, approval controls and how access is granted.
Capability keys spend.transactions · spend.expenses · spend.cards · spend.bills · spend.procurement · All tools
letme.dev/spend.transactions picks the top-graded tool in this list and says how to call it direct; calling through letme comes later.
The same listing from the live API. Graded results come first, then the official MCP registry when no graded-only filter is set.
https://www.anchorterminal.com/api/v1/searchFilters
| Compare | # | Tool | Category | Grade | Score | Agent rating | p95 | Context | Price / x402 | Auth | Where | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 263 | Pleo API + MCPPleo Technologies A/S · HTTP API | Spend | B | 62.9 | none | n/a | n/a | Paid | OAuth or key | Hosted | ||
|
Spend management platform from Pleo Technologies A/S in Copenhagen, covering company cards, expenses, reimbursements, invoices and accounting exports. Outside agents reach it through a hosted MCP server for expense work and a REST API built for accounting integrations. Top strength MCP server at mcp.pleo.io/mcp uses OAuth with PKCE and dynamic client registration, and acts with the connecting user's Pleo permissions Top weakness The pricing page lists MCP on the Optimise plan only (£18 per user per month, three users minimum, sold through a demo) |
||||||||||||
| 274 | Spendesk API + MCPSpendesk SAS · HTTP API | Spend | B | 62.3 | none | n/a | n/a | Paid | OAuth or key | Hosted | ||
|
Spend management platform from Spendesk SAS in Paris, covering company cards, expense claims, supplier invoices, purchase orders and accounting exports. Outside agents reach it through a REST API with scoped keys or OAuth, and a hosted MCP server. Top strength OpenAPI 3.1 definition with 106 operations, llms.txt and a Markdown copy of every docs page, all public without sign-in Top weakness No public price, free tier or self-serve signup. API access and demo credentials are requested from a Spendesk representative |
||||||||||||
| 310 | BrexBrex LLC · HTTP API | Spend | C | 60.7 | none | n/a | n/a | $12 / seat-mo | OAuth or key | Hosted | ||
|
Brex is a spend platform with corporate cards, expense management, bill pay, travel and business accounts. Its REST Developer API reads and writes cards, expenses, spend limits, vendors and transfers, and a hosted MCP server is in beta. Top strength Ten public OpenAPI 3 specs covering 115 operations, plus llms.txt and a Markdown twin of every docs page Top weakness The Expenses API update endpoint accepts only |
||||||||||||
| 384 | RampRamp Business Corporation · HTTP API | Spend | C | 57.3 | none | n/a | n/a | $15 / seat-mo | OAuth | Hosted | ||
|
Ramp is a finance platform with company cards, expense management, bill pay, procurement and travel. Its Developer API reads and writes transactions, receipts, funds, bills and purchase orders. A hosted MCP server and CLI work with the signed-in user's permissions. Top strength Public OpenAPI 3.0.2 spec with 260 operations, plus llms.txt and a plain-text export of every guide and the API reference Top weakness No public status page was found. status.ramp.com doesn't resolve, and no status link appears in the docs, help centre or trust centre pages read |
||||||||||||
Nothing matches these filters. .
p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.
How we test this category
One test company with a fixed set of card transactions in each listing's sandbox. The same tasks run through its API (list transactions, attach a receipt, code an expense, create a spending limit, read a bill). We check scopes, approval points and the audit record. In this run listings are graded from public evidence against the published checklist. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.
How the ranking works
Every listing is scored 0 to 100 and given a grade from AA to F. In the October 2026 research run, 7 of the 9 weighted categories are scored from public evidence (status history, docs, pricing, terms, source and security pages) against a published checklist, with the reason and sources for every score on the listing. Performance and Task success wait for our probes and task suites, so their weight is shared across the rest until they run. Negative events deduct up to 15 points. Read the methodology.
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.