Ledgerbackup

io.github.CloudCorpRecords由 GitHub 账号 CloudCorpRecords 发布v0.1.0更新于 Nov 5, 2026

Read-only backup and export of Xero accounting data: organisations, exports, manifests, downloads.

已验证STDIO仅桌面文件与存储金融

概览

AI 生成的概览

连接托管 Boxkite 服务的本地桥接,让助手列出已连接的会计组织,并以只读方式导出其数据。

可以做什么
  • 列出 Boxkite 账户下已连接的会计组织(Xero、Sage、Reckon、QuickBooks)
  • 为某个组织启动只读导出,并列出历史导出记录
  • 查询导出的状态、进度和建议的轮询间隔
  • 查看进行中导出的清单:包含的实体、记录与文件数量、校验和
  • 把已发现的文件映射到其所属的会计对象
  • 获取已完成 ZIP 的短期签名下载链接
适用场景
适合让助手备份或提取已连接的 Xero、Sage、Reckon 或 QuickBooks 组织中的会计数据,并一路跟踪导出直到拿到可下载的压缩包,无需离开对话。
运行要求
通过 npx 或 Docker 在本机运行,并联网把调用转发到托管的 Boxkite 端点。可选环境变量 BOXKITE_MCP_URL 可覆盖端点;可选 BOXKITE_API_KEY 会以 X-API-Key 请求头发送。清单未声明任何凭据,未设置该变量时不发送密钥头。
安装前请注意
启动导出按每个组织收费 39 美元,需在浏览器中完成 Stripe 结账;重复调用会返回已有导出而不会再次扣费。导出可能持续数小时,压缩包从几 MB 到数 GB 不等。下载链接为短期有效,并受 7 天保留期限制。工具调用及参数会转发给第三方 Boxkite 服务,若设置了 API 密钥,每次请求都会携带。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Ledgerbackup,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

ledgerbackup

ledgerbackup is a small local bridge to the hosted Boxkite MCP server, which backs up and exports accounting data from the organisations connected to your Boxkite account (Xero, Sage, Reckon, or QuickBooks). It lists those organisations, starts a read-only export of one organisation's data, and then tracks that export through its status, manifest and file-to-object mapping until a signed download URL for the finished ZIP is available.

The bridge keeps no accounting data of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched.

Tools

  • list_organisations — list the accounting organisations connected to the authenticated Boxkite account. No arguments.
  • start_export — start a read-only export of one organisation's data. Required: organisationId (from list_organisations). Per the upstream description, an export costs $39 per organisation: when payment is outstanding the response is status awaiting_payment with a Stripe checkout URL, and repeat calls return the existing export rather than creating or charging for a second one. A typical export runs for hours.
  • list_exports — list one-off exports, newest first, optionally filtered by organisationId. Side-effect free: it never starts an export or charges anything.
  • get_export_status — report one export's state (queued | running | ready | failed), its progress, and when to poll again. Required: exportId.
  • get_export_manifest — see what an in-progress export contains so far, paged via fileOffset and fileLimit. Required: exportId.
  • get_export_mapping — for an in-progress export, map each discovered file to the accounting object it represents, paged the same way. Required: exportId.
  • get_download_url — return a short-lived signed URL for the finished export ZIP, valid within the export's 7-day retention window. Required: exportId.

Configuration

  • BOXKITE_MCP_URL (optional) — override the upstream endpoint. Defaults to https://app.getboxkite.com/mcp. (The override hook is this rebuild's own labelled reconstruction.)
  • BOXKITE_API_KEY (optional) — when set, every upstream request carries an X-API-Key: <key> header with your Boxkite API key. When it is not set, no key header is sent. No Authorization header is ever sent. (This forwarding is also a labelled reconstruction; the original surface was captured keyless.)

Forwarding mechanics

On the first tool call the client opens a streamable HTTP session with the upstream: a JSON-RPC initialize request (protocolVersion 2025-03-26, clientInfo name ledgerbackup), then a notifications/initialized notification, then the tools/call request carrying the caller's arguments unchanged. When the upstream answers initialize with an Mcp-Session-Id header, that value rides on every later request of the session, which is reused for the life of the process. Replies may arrive as plain JSON or as server-sent events; both are read.

Successful upstream results pass through verbatim, including any isError flag the upstream sets. Failures — a JSON-RPC error, a non-2xx status, an unreadable response, or a request that cannot be completed — come back as an isError result whose text starts with ledgerbackup error: (this rendering is this rebuild's own labelled reconstruction).

CLI

Each tool is also a subcommand taking one JSON argument string:

bash
npx @reneturcios/ledgerbackup list_organisationsnpx @reneturcios/ledgerbackup start_export '{"organisationId":"org-123"}'npx @reneturcios/ledgerbackup get_export_status '{"exportId":"exp-9"}'npx @reneturcios/ledgerbackup get_download_url '{"exportId":"exp-9"}'npx @reneturcios/ledgerbackup --version

Exit codes: 0 on success, 1 on an isError result, 2 on a usage error.

MCP server

bash
npx -y @reneturcios/ledgerbackup mcp

MCP client config:

json
{  "mcpServers": {    "ledgerbackup": {      "command": "npx",      "args": ["-y", "@reneturcios/ledgerbackup", "mcp"]    }  }}

Docker

bash
docker run -i ghcr.io/cloudcorprecords/ledgerbackupdocker run --rm ghcr.io/cloudcorprecords/ledgerbackup --version

The container's default command is mcp, so the first form is a stdio MCP server; any other arguments reach the CLI normally.

Development

bash
npm installnpm run buildnpm testnpm run dev

The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.

License

MIT — see LICENSE.

来源:README.md,提交 9b4133b

工具

7

list_organisations

List accounting organisations

List the accounting organisations (Xero, Sage, Reckon, or QuickBooks) connected to the authenticated Boxkite account.

无需输入参数。

start_export

Start a one-off accounting data export

Starts a read-only export of one accounting organisation's data (Xero, Sage, Reckon, or QuickBooks). Costs $39 per organisation: when payment is outstanding the response is status 'awaiting_payment' with a Stripe checkoutUrl for the user to complete in a browser, and the export begins once that payment settles. This is not a status endpoint: it reports only the state at creation, and repeat calls return the existing export for that organisation rather than creating or charging for a second one. Export progress is reported by get_export_status, and newly created exports appear in list_exports. A typical export runs for hours, and pauses whenever it meets a provider rate limit or Boxkite's egress budget — anything from under a minute to the next UTC day. get_export_status reports when it resumes.

输入参数organisationId必填

list_exports

List exports

List one-off exports (newest first), optionally for one organisation. Use this to find an export after payment and to poll its status until it is 'ready'. Side-effect free: it never starts a new export or charges anything. Each entry carries progress, parkedUntil and pollAfterSeconds.

输入参数organisationId

get_export_status

Get export status

Reports the state of one export: status (queued | running | ready | failed) and whether its download is available yet. Also returns progress {discovered, transferred, percent}; parkedUntil; and pollAfterSeconds, the interval after which this status is expected to have changed. A large export runs for hours, so pollAfterSeconds can be a long interval. parkedUntil is a timestamp, present whenever work on the organisation is paused and expected to resume. How long varies by cause and is not worth guessing at: hitting Xero's per-minute limit pauses for under a minute, approaching its daily quota pauses for about an hour, and exhausting the daily quota or Boxkite's own egress budget pauses until the next UTC day. Wait until the timestamp (or pollAfterSeconds, which already accounts for it) rather than describing a cause to the user.

输入参数exportId必填

get_export_manifest

Get export manifest

See what an IN-PROGRESS export contains so far (entities included, per-entity record/file counts, and per-file checksums), growing as discovery and downloading proceed. The per-file list is paged: check filesPage.hasMore and pass fileOffset to walk it. Once the export finishes, this returns status 'complete' with a pointer instead of a list, because the full manifest travels inside the ZIP as manifest.json: get a download URL, then read manifest.json from the archive.

输入参数exportId必填fileLimitfileOffset

get_export_mapping

Get export file→object mapping

For an IN-PROGRESS export, get the mapping of each file discovered so far to the accounting object it represents or is attached to (e.g. which invoice a receipt PDF belongs to). Paged (default 200 files, max 500): check filesPage.hasMore and pass fileOffset for the next page; the `objects` map covers only the files on the current page. Once the export finishes, this returns status 'complete' with a pointer instead: the full mapping ships under Info/ inside the ZIP, so download the archive and read Info/files.json from it.

输入参数exportId必填fileLimitfileOffset

get_download_url

Get export download URL

Returns a short-lived signed URL for the export ZIP, valid within the export's 7-day retention window, along with byteSize (the archive's size in bytes, null if unavailable) and fileCount. These archives range from a few MB to several GB. The archive contains the exported files plus manifest.json (every file with its sha256) and Info/ (the file-to-Xero-object mapping).

输入参数exportId必填

版本历史

1
  1. v0.1.0最新Nov 5, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分
  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分