Niches · Spend management & procurement

Fill in missing receipts, memos and coding on expenses

No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.

0companies, full fit
7companies, fit with a limit
10companies carry the tag
22share of the category's work
2first-hand accounts

What counts as done

Each receipt attached to the matching transaction (by amount, date and merchant) through the API, each memo, category and custom field set, a re-sent receipt not creating a duplicate, and the change visible on a re-read with the agent named in the audit record.

How agents ask for it: find transactions missing receipts, attach this receipt to the Uber charge, code these expenses to the right GL accounts, chase people for missing memos

Does the job, with a limit 7

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
BILL B
Bill.com, LLC
Receipts attach to transactions and reimbursements through an upload URL, PUT transaction custom-fields sets coding, and PUT updates the transaction. No idempotency key on the 203 writes, and the audit trail endpoint covers vendors only. source
Brex B
Brex LLC
Receipt upload gives a pre-signed URL per expense, receipt match pairs loose receipts, compliance_status DUE or OVERDUE finds missing ones, and POST /v3/accounting/records sets fields on up to 50 expenses. The expense update itself takes only memo, and no duplicate guard or agent audit trail was found. source
Mercury API B
Mercury Technologies, Inc.
Upload a transaction attachment and update the note and custom category per transaction; GL accounts and other accounting fields are not settable, no duplicate guard on attachments was found, and writes need an IP-allowlisted token. source
Payhawk API + MCP C
Payhawk Limited
POST expenses/{id}/files imports a receipt, PATCH expense, custom-field and line-item endpoints set coding, and GET files reads them back. No duplicate guard on file imports was found, and whether the audit log names an API key was not read. source
Pleo API + MCP B
Pleo Technologies A/S
The MCP is built for this: find incomplete expenses, attach missing receipts, recategorise in bulk and code VAT, acting as the signed-in user; the Enrichment API attaches receipts to card entries. MCP tool names and schemas are unpublished, and no duplicate guard was found. source
Ramp C
Ramp Business Corporation
POST /receipts (multipart) attaches to a transaction_id or auto-matches, POST /memos sets memos, POST /accounting/codings and PATCH transactions (beta) set accounting fields, and the audit log filters by agent_names on Plus. No duplicate guard is documented for receipt uploads, and the MCP cannot pass files. source
Spendesk API + MCP B
Spendesk SAS
PATCH payables/{id} sets accounting fields, payable attachments can be uploaded and listed, and mark-as-ready moves them on; all under experimental scopes, with no duplicate guard on attachment uploads and no agent named in an audit read. source

Doesn't do this job 2

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

ListingWhy
Airwallex Spend and Issuing B
Airwallex US, LLC
The card expense API lists, retrieves and sets sync status only; there is no call to attach a receipt, set a memo or code accounting fields on an expense. source
Expensify F
Expensify, Inc.
The expense creator makes new expenses with category, tag, comment, tax and externalID, but nothing updates an existing expense or attaches a receipt file to it; receiptURL appears only in export data. source

What stops agents finishing

  • MCP cannot pass a receipt file, so receipts are uploaded in the app (Ramp support page)
  • update endpoint accepts only the memo, so category and custom fields cannot be set (Brex)
  • no endpoint to attach a receipt or code an expense (Airwallex)

Around it

Before: email.find-attachment, document-extraction.receipt-fields. After: spend-management.sync-to-books.

Where this comes from

Weight 22 of 100 in Spend management & procurement: 2 of 18 accounts (acc-01, acc-16); weight set by hand from Ramp's figure that 62% of its assistant usage is completion work such as coding and attaching receipts (vendor figure)

The same as data: /api/v1/use-cases/spend-management.complete-expenses.json, or the MCP tool get_use_case with id spend-management.complete-expenses. 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.