広告掲載
MCP.so
ログイン

Kelnix Receipt MCP Api

@kelnixsolutions

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

kelnixsolutions

投稿者

Kelnix

Kelnix Receipt MCP Api について

Description: Turn any receipt into structured, accounting-ready JSON or clean Markdown with one API call. AI-powered vision

#receipts#accounting#expense#ocr#ai-vision#bookkeeping#mcp

Kelnix Receipt MCP Api の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "kelnix-receipt": {
      "command": "python",
      "args": [
        "mcp_server.py"
      ],
      "env": {
        "RECEIPT_MCP_API_KEY": "<YOUR_API_KEY>",
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_KEY>"
      }
    }
  }
}

Kelnix Receipt MCP Api のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Kelnix Receipt Mcp Api?

An MCP API that uses AI vision to parse receipts into structured, accounting-ready JSON. It extracts merchant, date, line items, tax, totals, and suggests GL accounts for instant bookkeeping. Designed for AI agents automating expense management, accounts payable, and bookkeeping.

How to use Kelnix Receipt Mcp Api?

Register via POST /register_agent to get an API key and 50 free credits. Then call POST /tools/upload_and_process with a receipt image (costs 1 credit). When credits run low, buy more via Stripe or 300+ cryptocurrencies. The server can also be self-hosted with Python 3.11+.

Key features of Kelnix Receipt Mcp Api

  • AI vision extraction of receipt data and line items
  • Suggests GL accounts for accounting entries
  • Credit-based pricing with free tier and subscriptions
  • Crypto payments for 300+ coins
  • MCP protocol compatible with Claude Desktop, Cursor
  • Ready-to-use code for LangGraph, CrewAI, AutoGen

Use cases of Kelnix Receipt Mcp Api

  • Automate expense report creation from receipt photos
  • Streamline accounts payable by extracting vendor and totals
  • Feed structured receipt data into bookkeeping software
  • Enable AI agents to handle receipt processing autonomously

よくある質問

1

How do I get an API key?

Call `POST /register_agent` with your agent name. You instantly receive an API key and 50 free credits.

2

How much does it cost?

Each receipt processing and GL account suggestion costs 1 credit. Credits start at $5 for 100. Subscriptions from $15/mo (200 credits) are also available.

3

Can I pay with cryptocurrency?

Yes. Use `POST /billing/buy_credits_crypto` to pay with BTC, ETH, SOL, USDC, USDT, DOGE, and over 280 other coins.

4

Can I self-host this server?

Yes. Clone the repository, install dependencies, set `ANTHROPIC_API_KEY`, and run with uvicorn. Requires Python 3.11+.

5

What transport and authentication does the server use?

All tool and billing endpoints require the `X-API-Key` header. The server communicates over HTTP and follows the MCP protocol for discovery via `/.well-known/mcp.json`.

コメント

「開発者ツール」の他のコンテンツ

Modelglass

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

1

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

1

Mcp-Warden

ermoluk

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

4

Final POS – Custom POS Builder

Final Commerce

Build custom POS apps with your AI agent. Final's MCP server lets developers scaffold checkout flows, adapt vetted screen blueprints for counter POS, self-checkout kiosks, restaurant ordering and payment terminals, previ

MCP Server By TestMu AI

TestMu AI

TestMu AI MCP Server lets developers run, debug, and triage tests through natural language directly from their IDE (Cursor, Claude, GitHub Copilot, and other MCP clients). It exposes five tools — HyperExecute (test orche

広告掲載