SolidInvoice
Create and send invoices and quotes, manage clients, and track payments in SolidInvoice.
Invoices, receipts and statements into clean rows you can check and export. REST API and MCP.
作者提供的原文
此项在“连接 AI 的应用”标签中,该标签不使用星标,按以下顺序排列
| 1. 在 Claude 连接器目录中 | 否 | |
|---|---|---|
| 2. 团队实测过 | 否 | |
| 3. 适合泰国用户 | 否 | |
| 4. 不计星标的使用量 | 20/100 | 热度 0 · 新鲜度 12 · 仍在响应 8 · 用户喜欢 +0 |
| 5. 登记日期 | 2026-11-20 |
用户喜欢: 0 · 最多加 5 分(每人 1 分),不能用钱买。
质量: 基础检查通过 4/4 项(仅展示,不用于排序)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Doxtract。按照 https://mcp.popnx.com/i/manoonlabs-doxtract.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 4/4 项检查 · 你的提问会经过开发者的服务器(doxtract.manoonlabs.com) · ✓ 命令已检查 2026年11月21日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 5 分钟
需要 Doxtract 的密钥(在开发者网站创建) · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
名称和地址已为你填好,核对后点击 Add · 如果没有登录,Claude 会先让你登录
在 Request headers 下添加这个名称和值
AuthorizationBearer <在这里粘贴你的密钥>只把密钥粘贴到应用的输入框里,不要粘贴到聊天中或发给任何人
在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
CustomizeConnectors
点击“Add” → “Custom” → “Web”,填写这 2 项
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Doxtracthttps://doxtract.manoonlabs.com/mcp+ConnectorsDoxtract
用 Doxtract 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Doxtract,或回答中出现 Doxtract 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Doxtract
Doxtract 连接时需要你自己的密钥,但 OpenAI 帮助页面只说明了 OAuth 登录,没有我们能核实的填密钥方式
A · 使用能连接 Doxtract 的应用
B · 会计、财务与税务 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
可连接 Claude Code · 约 5 分钟
需要 Doxtract 的密钥(在开发者网站创建)
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user doxtract https://doxtract.manoonlabs.com/mcp --header 'Authorization: Bearer your-value'按 Enter 前,把“your-value”改成你的密钥
只把密钥粘贴到应用的输入框里,不要粘贴到聊天中或发给任何人
应能看到 Doxtract 在列表中并显示已连接
用 Doxtract 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Doxtract,或回答中出现 Doxtract 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 5 分钟
需要 Doxtract 的密钥(在开发者网站创建)
在 Doxtract 的设置中,Authorization 还是空的,填入你的密钥并保存
只把密钥粘贴到应用的输入框里,不要粘贴到聊天中或发给任何人
用 Doxtract 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Doxtract,或回答中出现 Doxtract 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 5 分钟
需要 Doxtract 的密钥(在开发者网站创建)
在 Doxtract 的设置中,Authorization 还是空的,填入你的密钥并保存
只把密钥粘贴到应用的输入框里,不要粘贴到聊天中或发给任何人
用 Doxtract 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Doxtract,或回答中出现 Doxtract 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
Claude Code
claude mcp add --transport http --scope user doxtract https://doxtract.manoonlabs.com/mcp --header 'Authorization: Bearer your-value'Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"doxtract": {
"url": "https://doxtract.manoonlabs.com/mcp",
"headers": {
"Authorization": "Bearer your-value"
}
}
}
}VS Code (mcp.json)
{
"servers": {
"doxtract": {
"type": "http",
"url": "https://doxtract.manoonlabs.com/mcp",
"headers": {
"Authorization": "Bearer your-value"
}
}
}
}说明为自动翻译,变量名保持原样;不确定时请查看原文。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
工具名称和描述与服务器在 2026年11月21日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
whoamiReturn the workspace and token for the bearer credential, and the credits left this month.
parse_documentExtract structured fields from a PDF, PNG, JPEG, or text file sent as base64 in file_base64, or from plain text sent in text (10 MB and 10 pages on Free, 25 MB on Starter and Pro, 100 MB on Business; pages per document by plan: Starter 50, Pro 200, Business 500). 1 credit per pag
list_schemasList the extraction layouts saved in this workspace.
get_schemaRead one saved extraction layout by slug.
create_schemaSave an extraction layout in this workspace. The slug (API id) is derived from the display name. A layout is {"type":"object","properties":{...}}. Each property is {"type":T} where T is one of any, null, boolean, string, number, date, array, object. An optional description, at mo
update_schemaUpdate a saved layout's display name and/or definition. A layout is {"type":"object","properties":{...}}. Each property is {"type":T} where T is one of any, null, boolean, string, number, date, array, object. An optional description, at most 400 characters, tells the model how to
list_inboxesList the inboxes this key can see, newest first, up to 200. Each has its id, name, icon, status, document count and email address. A key limited to some inboxes sees only those.
get_inboxRead one inbox: its name, icon, status, document count, email address, and its fields as a JSON schema (schema, null for a draft with no fields yet). The fields show what kind of document the inbox reads, so use them to decide which inbox a document belongs in.
upload_documentAdd one document to an inbox. It is read with the inbox's fields in the background, the same as a document dropped into the inbox in the console, and costs 1 credit per page. Send the file as file_base64 (a PDF, PNG or JPEG) with its file_name. Returns the new document's id. Uplo
create_inboxCreate an inbox in this workspace and return its id and email address. Send template (a built-in template slug: invoice, receipt, bank_statement, purchase_order) to make it ACTIVE with that template's fields, the same as creating one in the console. Without a template it is a DRA
create_inbox_from_schemaCreate an active inbox from a schema you send, in the same format as a saved layout. The inbox gets its own fields, its email address is returned, and mail and uploads are parsed at once. This path is for the API and MCP only; the console does not offer it.
update_inboxChange an inbox's name and/or icon. Send name, icon, or both. Send icon as null to go back to the default icon. Renaming does not change the email address.
get_inbox_emailRead an inbox's email address and whether it accepts mail. The address is created the first time it is read.
set_inbox_email_enabledTurn mail receiving on or off for one inbox. The address does not change. Documents already in the inbox are not affected.
set_inbox_webhookSave where an inbox sends each parsed document, so documents that arrive by email or upload reach your system without a poll. Each body is signed with the returned secret. An empty url turns the webhook off. Only a key created by the workspace owner can change it.
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月21日
注册名称已通过域名 manoonlabs.com 验证(注册中心会核实域名所有权)
代码最后更新于今天
不适用:由 manoonlabs.com 的所有者自己运行的云端服务器,你不会运行仓库里的代码
在 335 毫秒内响应(HTTP 200)
无需登录
已读取 15 个工具描述,未发现针对 AI 的隐藏指令
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/manoonlabs-doxtract)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 4 项适用的基础检查中通过了 4 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:Authorization
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于今天,最新版本(1.2.0)于今天进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同一分类中有:SolidInvoice, Journalit, Beancount.io, Tapetide - Indian Stock Market MCP, Twelve Data
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Create and send invoices and quotes, manage clients, and track payments in SolidInvoice.
Trading journal in Obsidian. Ask Claude or ChatGPT about your trades; edits are previewed first.
Query, edit, and reconcile a hosted Beancount ledger: BQL, reports, files, and bank imports.
48 tools for ~8,000 NSE & BSE stocks: quotes, screener, financials, filings, FII/DII, options
Real-time and historical market data: stocks, forex, crypto, ETFs, fundamentals and 60+ indicators.
| 本项 Doxtract | SolidInvoice | Journalit | Beancount.io | Tapetide - Indian Stock Market MCP | Twelve Data | |
|---|---|---|---|---|---|---|
| 运行位置 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 云端或安装在电脑上都可以 | 在云端运行,无需安装 |
| 需要密钥 | 是 | 否 | 否 | 否 | 是 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 否 | 是 |
| 基础检查 | 4/4 | 4/6 | 4/4 | 4/4 | 5/5 | 4/4 |
| 许可证 | MIT | MIT | NOASSERTION | MIT | MIT | – |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Get an API key · API docs · Playground · MCP server · Benchmark
The official JavaScript and TypeScript SDK for Doxtract. Send a PDF, scan, phone photo or text, plus the schema you want. Get back JSON in that shape. If a field isn't on the document, you get null, not a guess.
import { Doxtract } from "@manoonlabs/doxtract";
import { z } from "zod";
const doxtract = new Doxtract(); // reads DOXTRACT_API_KEY
const Invoice = z.object({ vendor: z.string().nullable(), total: z.number().nullable() });
const { values } = await doxtract.parse("invoice.pdf", { schema: Invoice }); values.total; // number | null
values is typed from it, or use parse () for values: T. Errors come back as classes you can instanceof.zod as a peer, for Zod schemas. It's built on native fetch and FormData, ships as ESM and CommonJS, and runs server-side on Node 18+, Bun and Deno.We ran Doxtract and a plain LLM prompt over 45 public documents with the same schema, then scored every field against a hand-checked answer key.
| Fields extracted correctly | Doxtract | Plain LLM prompt |
|---|---|---|
| All fields | 98.7% | 69.7% |
| Rotated pages | 100% | 39.3% |
| Phone photos | 96.2% | 56.4% |
| Made-up values per 100 fields (all 50 docs) | 0.1 | 1.9 |
The method, caveats and per-document CSV are on the benchmark page.
Every extracted value links back to where it came from. Click a value to see its box on the document, or click a box to jump to the value.
In the SDK, set citations: true:
const result = await doxtract.parse("invoice.pdf", { schema: Invoice, citations: true });
result.citations?.["total"]; // { page: 1, text: "Total 1,280.50", bbox: [0.62, 0.81, 0.91, 0.84], status: "verified", source: "text_layer" }
total or lineItems[0].amount.page is null for a text document.[x0, y0, x1, y1] as fractions of the page from the top left, or null when there's no box.verified, fuzzy, mismatch, other_page or unverified, from checking the text against the page.npm install @manoonlabs/doxtract
pnpm add @manoonlabs/doxtract yarn add @manoonlabs/doxtract bun add @manoonlabs/doxtract
On Deno, import npm:@manoonlabs/doxtract.
zod (version 4) is a peer dependency, used only when you pass a Zod schema. npm 7 and later and pnpm install it for you. On Yarn, run yarn add zod if you want Zod schemas. Plain schemas work without it.
export DOXTRACT_API_KEY=bk_live_...
import { Doxtract } from "@manoonlabs/doxtract";
import { z } from "zod";
const doxtract = new Doxtract({ apiKey: process.env.DOXTRACT_API_KEY });
const Invoice = z.object({ vendor: z.string().nullable(), total: z.number().nullable(), });
const result = await doxtract.parse("invoice.pdf", { schema: Invoice });
console.log(result.values); // { vendor: "Northwind Supply", total: 1280.5 }
Not using Zod? Pass a plain JSON schema or a saved schema name instead. See Without Zod.
If you leave out apiKey, the client reads DOXTRACT_API_KEY, then DOC2JSON_API_KEY. If there's no key at all, the constructor throws a DoxtractError with code missing_api_key. Doc2Json and Doc2JsonError are still exported.
Want to see the output before writing code? Run a sample invoice in the Playground. No sign-in needed.
parse() takes the document in whatever form you have it:
import { readFile } from "node:fs/promises";
// A file path (Node, Bun and Deno) await doxtract.parse("./invoice.pdf");
// Bytes: Buffer, Uint8Array or ArrayBuffer await doxtract.parse(await readFile("invoice.pdf"), { filename: "invoice.pdf" });
// A Blob or File, for example from an await doxtract.parse(input.files[0]);
// Base64 (a data: URL prefix is removed for you) await doxtract.parse({ base64: pdfBase64, filename: "invoice.pdf" });
// Plain text, such as an invoice email await doxtract.parse({ text: "Invoice INV-1042 from Northwind Supply. Total 1280.50 USD." });
Without a schema, Doxtract chooses the fields. To control the output, pass a Zod schema, a plain JSON schema, or the name of a schema saved in your workspace.
Pass a Zod 4 schema and values is typed with z.infer. There's no JSON to write and no generic to add. The SDK converts the schema for you:
import { z } from "zod";
const Invoice = z.object({ vendor: z.string().nullable(), total: z.number().nullable(), issued: z.iso.date().nullable(), // yyyy-mm-dd lineItems: z.array(z.object({ description: z.string(), amount: z.number() })), });
const result = await doxtract.parse("invoice.pdf", { schema: Invoice });
result.values.total; // number | null result.validation.success; // true when values match Invoice
null for a missing value, and .nullable() keeps your types honest..describe("...") tells Doxtract how to read a field.[] when there are no rows.validation, which is schema.safeParse(values). A mismatch never throws. Check validation.success, and read validation.error.issues for the details. values is always the JSON the API sent, so read validation.data if your schema uses transforms or z.coerce.zod is a peer dependency. npm 7 and later install it with the SDK, so there's usually nothing to do.z.string(), z.number() (and .int()), z.boolean() and z.object() map to the same Doxtract types. z.iso.date() becomes date, sent back as a yyyy-mm-dd string. An enum becomes a string with the allowed values added to the hint, and a literal becomes its own type. .optional() drops the key from required. Shapes with no Doxtract type, such as a union of two types, z.record() or z.unknown(), become any. Checks like .min() or .regex() aren't sent, but validation still applies them.z.date() also becomes date, but the API still sends a string. Use z.coerce.date() and read validation.data to get a Date.zodToSchema(Invoice) returns the definition the SDK sends.zod/mini schemas work too. Zod 3 schemas don't, so upgrade to zod@4.Pass the definition as a plain JSON schema object, and add the type yourself with parse ():
type Invoice = {
vendor: string | null; total: number | null; issued: string | null; // yyyy-mm-dd lineItems: { description: string; amount: number }[]; };
const result = await doxtract.parse ("invoice.pdf", { schema: { type: "object", properties: { vendor: { type: "string" }, total: { type: "number" }, issued: { type: "date" }, lineItems: { type: "array", items: { type: "object", properties: { description: { type: "string" }, amount: { type: "number" }, }, required: ["description", "amount"], }, }, }, required: ["vendor", "total"], }, });
result.values.total; // number | null
string, number, boolean, date, array, object, null and any.date comes back as yyyy-mm-dd.description to any field to tell Doxtract how to read it.null.[] when there are no rows.zod installed.Save a schema once and refer to it by name from every app, key and MCP client in the