`get_claims`

Read-only

Calls GET /api/claims as the signed-in person · REST reference

The claim queue

The same projection as GET /api/claims/recent, with a caller-supplied page size. Both call the same service method under the same org scope; the only difference is the limit. limit is an OUTPUT CAP, not a page size. The service always asks the DAL for the newest 200 vouchers in any state, filters those to claim states, then slices — so a limit above roughly 200 cannot yield more rows, and a busy period of non-claim vouchers can push real claims out of the window regardless of the value sent. There is no offset and no total.

Arguments

Argument	Type		Description
`limit`query	integer		Clamped to at most 200. A non-numeric or zero value falls back to 50 rather than erroring.

Example call

A client sends this over the MCP session; Claude and other agents build it for you. The values are placeholders — the shape is real.

json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_claims",
    "arguments": {}
  }
}

Result

On success (HTTP 200) the tool returns one text item holding the API's JSON, pretty-printed.

A bare array of claim rows, newest first.

json

[
  {
    "amount": 1,
    "currency": "string",
    "id": "11111111-1111-4111-8111-111111111111",
    "status": "string",
    "voucherCode": "string",
    "voucherId": "11111111-1111-4111-8111-111111111111",
    "claimedAt": 1,
    "claimedByOrgId": "11111111-1111-4111-8111-111111111111",
    "procedure": "string",
    "workOrderId": "string"
  }
]

Fields

Field	Type	Description
`[].amount`	integer \| null	The value of the voucher's claim in CENTS — the only money a voucher is shown as worth, derived by the backend (`claimAmount`, backend/src/domain/claimInvoice.ts), not a DAL field. Null until the claim is submitted, and while a CLAIMED voucher's invoice waits on the AI or a reviewer; a CLAIMED voucher's validated covered amount, capped as approval caps it; from APPROVED on, what approval credited (`creditedAmount`). Never the face value (`value`).
`[].claimedAt`	integer \| string	Epoch milliseconds, or an ISO string on rows written before the scalar.
`[].claimedByOrgId`	string (uuid)
`[].currency`	string
`[].id`	string (uuid)	The voucher id.
`[].procedure`	string
`[].status`	string	The voucher state.
`[].voucherCode`	string
`[].voucherId`	string (uuid)
`[].workOrderId`	string

When it fails

A failed call returns isError: true with the API's message as text.

403: The caller holds no voucher feature in any organization.
404: The DAL's refusal said "not found".

What the model is shown

This is the tool exactly as the server lists it in tools/list. The description starts with the REST call it makes.

json

{
  "name": "get_claims",
  "description": "GET /api/claims — The same projection as `GET /api/claims/recent`, with a caller-supplied page size. Both call the same service method under the same org scope; the only difference is the limit. `limit` is an OUTPUT CAP, not a page size. The service always asks the DAL for the newest 200 vouchers in any state, filters those to claim states, then slices — so a `limit` above roughly 200 cannot yield more rows, and a busy period of non-claim vouchers can push real claims out of the window regardless of the value sent. There is no offset and no total.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "limit": {
        "type": "string",
        "description": "Clamped to at most 200. A non-numeric or zero value falls back to 50 rather than erroring."
      }
    }
  },
  "annotations": {
    "readOnlyHint": true,
    "openWorldHint": false
  }
}