AIDataParser

io.github.shibley由 GitHub 帳號 shibley 發布v0.2.0更新於 Oct 24, 2026

PDFs, images and messy text to schema-guaranteed JSON. try_parse runs a real extraction, no key.

發布方自己的服務：Parser Club

已驗證Streamable HTTP可網頁執行檔案與儲存資料與分析

服務詳細資訊

識別碼: io.github.shibley/aidataparser
傳輸: Streamable HTTP
執行環境: Web executable
信任: Verified
發布於: Sep 22, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此條目所屬的 GitHub 帳號 shibley。這並不表明該帳號就是產品方。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.shibley%2Faidataparser.svg)](https://sourceweft.com/mcp/io.github.shibley%2Faidataparser?utm_source=readme&utm_medium=badge)

概覽

AI 產生的概覽

AIDataParser 是託管式 MCP 伺服器，可將 PDF、圖片和雜亂文字轉為符合 schema 的 JSON，提供免費試用擷取與以點數計費的付費解析。

可以做什麼: 對最多 4000 字元的文字執行免費試用擷取，無需金鑰或帳號即可預覽輸出結構，每天限 3 次。從以 URL 或 base64 提供的 PDF、圖片擷取受 schema 約束的 JSON，也可從抓取網頁、郵件內容、聊天記錄或 OCR 結果等原始雜亂文字擷取。依一份樣本文件推斷可重複使用的 JSON Schema，並列出內建範本（如發票、收據、履歷）。依 schema 或內建範本驗證 JSON 物件並回傳逐欄位錯誤。透過電子郵件建立 API 金鑰、查詢剩餘點數，並取得點數方案的 Stripe 結帳連結。
適用情境: 當助理需要把發票、收據、履歷、掃描文件或非結構化文字轉為遵循固定 schema 的結構化 JSON 時使用，也適合在付費前先測試擷取品質。它面向文件處理與資料登錄流程，而非通用檔案儲存或搜尋。
執行需求: 遠端 Streamable HTTP 端點，無需本機執行環境或安裝套件。免費工具 try_parse、list_schemas 和 validate 無需金鑰。付費工具需要 AIDataParser API 金鑰，可透過 create_api_key 提供電子郵件取得，或使用金鑰端點，並以 Authorization Bearer 標頭設定。每份文件消耗點數。

安裝前請注意

create_api_key 需要使用者電子郵件並回傳有效 API 金鑰，應將該金鑰視為機密。parse_document 和 parse_text 會把文件內容或文字傳送給第三方服務，且每次消耗 1 點數。buy_credits 回傳真實付款的 Stripe 結帳連結，購買的點數會記入所設定金鑰的帳戶。免費試用每天限 3 次。

安裝

在 SourceWeft 中

開啟儀表板中的 AIDataParser，將其新增到工作區。
為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.shibley%2Faidataparser/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "aidataparser": {
      "type": "http",
      "url": "https://aidataparser.com/v1/mcp"
    }
  }
}

README

AIDataParser MCP server

The official Model Context Protocol registry record for AIDataParser — a credit-based data-extraction API that turns PDFs, images and messy text into schema-guaranteed JSON.

There is no server code in this repo. The MCP server is hosted: it lives at https://aidataparser.com/v1/mcp and speaks JSON-RPC 2.0 over Streamable HTTP. This repo holds the server.json that is the source of our record in registry.modelcontextprotocol.io, the canonical upstream every downstream MCP catalog syncs from.

Add it to your client

json

{  "mcpServers": {    "aidataparser": {      "type": "http",      "url": "https://aidataparser.com/v1/mcp",      "headers": { "Authorization": "Bearer adp_live_..." }    }  }}

{  "mcpServers": {    "aidataparser": {      "type": "http",      "url": "https://aidataparser.com/v1/mcp",      "headers": { "Authorization": "Bearer adp_live_..." }    }  }}

Try it before you sign up. try_parse runs a real extraction with no key, no email and no account — up to 4,000 characters of text, 3 calls per day. Add the server without the headers block and call it:

json

{ "name": "try_parse", "arguments": { "text": "INVOICE #1042 ... Total due $1,240.00", "schema_id": "invoice" } }

{ "name": "try_parse", "arguments": { "text": "INVOICE #1042 ... Total due $1,240.00", "schema_id": "invoice" } }

When you want more, get a key (50 free credits, no card) — over MCP with the create_api_key tool, or:

bash

curl -X POST https://aidataparser.com/v1/keys \  -H 'Content-Type: application/json' \  -d '{"email":"[email protected]"}'

curl -X POST https://aidataparser.com/v1/keys \  -H 'Content-Type: application/json' \  -d '{"email":"[email protected]"}'

Tools

Tool	Cost	What it does
`try_parse`	free, no key	Real extraction on ≤4,000 chars of text, 3/day — see the output before signing up
`create_api_key`	free, no key	An email → a live `adp_live_` key with 50 free credits
`parse_document`	1 credit	PDF or image (`url` or `base64`) → JSON matching your schema
`parse_text`	1 credit	Raw/messy text → JSON matching your schema
`infer_schema`	1 credit	One sample → a reusable JSON Schema
`validate`	free, no key	Check a JSON value against a schema
`check_credits`	free	Credits remaining on the key
`list_schemas`	free, no key	Built-in templates (invoice, receipt, resume, …)

Credit packs: https://aidataparser.com/pricing

Publishing

.github/workflows/publish-mcp.yml publishes on a push to main using GitHub OIDC — no secrets. Bump version in server.json to cut a release; a push that does not change the version is a no-op.

Before it publishes, the workflow runs two gates:

npm test — static checks on server.json (validate-server-json.mjs). Each rule maps to a real failure from a sibling repo, e.g. the registry's 100-char description cap that 422'd aisotools-mcp-server v0.1.0.
npm run check:remote — a live initialize + tools/list handshake against the URL about to be advertised. A registry record pointing at a dead endpoint is worse than no record.

Both are runnable locally.

來源：README.md，提交 0f4d885

工具

try_parse

Try it now — parse text into JSON with no API key

Run a REAL extraction with no API key, no email and no signup, so you can see the output shape before committing to anything. Pass up to 4000 characters of messy text in `text` (an invoice, a receipt, a resume, scraped HTML, an email body) and optionally a `schema` or `schema_id` to constrain the result. Returns the same structured data, confidence and review_needed flag the paid tools return. Limited to 3 calls per caller per day — for real volume call create_api_key for 50 free credits, then use parse_text or parse_document.

輸入參數text必填schemaschema_idinstructions

create_api_key

Get an API key with free credits

Start here if you do not have an AIDataParser API key. Provide the user's `email` and receive a live adp_live_ API key with 50 free credits — no card, no signup form. Configure it on this MCP server as `Authorization: Bearer <api_key>` to unlock parse_document, parse_text and infer_schema. The key is returned ONCE and is never shown again, so surface it to the user and store it. Ask the user for their address; do not invent one. Free — does not consume a credit.

輸入參數email必填

parse_document

Parse a document into structured JSON

Extract clean, schema-guaranteed JSON from a PDF or image. Provide the document via `url` or `base64`. Pass an optional JSON `schema` to constrain the output shape, and `instructions` to guide extraction. Returns the extracted data plus a confidence score and a review_needed flag. Costs 1 credit per successful call.

輸入參數urlbase64redactschemaschema_idmedia_typeinstructions

parse_text

Parse raw text into structured JSON

Extract clean, schema-guaranteed JSON from raw/messy text you already have — scraped web content, email bodies, chat logs, OCR output, or pasted tables. Pass the text in `text`. Use this instead of parse_document when you don't have a file. Optional JSON `schema` (or `schema_id`) constrains the output shape and `instructions` guides extraction. Returns the extracted data plus a confidence score and a review_needed flag. Costs 1 credit per successful call.

輸入參數text必填redactschemaschema_idinstructions

infer_schema

Infer a reusable JSON Schema from a sample

Given one sample document's `text`, propose a reusable JSON Schema for that document type. Use this when no built-in schema_id fits: infer a schema once, review it, then reuse it as `schema` on parse_document / parse_text across many documents for consistent output. Returns the JSON Schema plus a flat field list and an inferred doc_type. Costs 1 credit per successful call.

輸入參數text必填doc_typeinstructions

validate

Validate JSON against a schema

Check whether a JSON object conforms to a JSON `schema` (or a built-in `schema_id` template) and get back a valid flag plus per-field errors. Use this to verify data you already hold — a prior parse result, your own output, or an upstream feed — before acting on it or spending a credit. Deterministic, free, and needs no API key.

輸入參數data必填schemaschema_id

check_credits

Check remaining credits

Return the number of extraction credits remaining on the authenticated API key. Free — does not consume a credit.

無需輸入參數。

list_schemas

List built-in schema templates

Return the built-in schema templates you can pass to parse_document as `schema_id` (invoice, receipt, resume, etc.), each with its id and the fields it extracts. Free — does not consume a credit and needs no API key.

無需輸入參數。

buy_credits

Buy a credit pack (returns a checkout link)

Get a Stripe checkout link for a one-time credit pack, to hand to the user. Packs: `starter` $9 for 500 credits, `growth` $29 for 2,000 credits, `scale` $99 for 10,000 credits. Credits never expire; 1 credit per document. If this server has an API key set, the credits land on that key's account. Without a key, pass the user's `email` (ask them; do not invent one) — the page after payment shows their new API key. Creating the link charges nothing; the user pays on Stripe's page.

輸入參數packemail