TunaPay TX Classifier
Classifies Solana on-chain transactions into tax categories (e.g., swap, stake, NFT) and exports CSV reports compatible with TurboTax and CoinTracker.
README
TunaPay TX Classifier
中文简介:TunaPay TX Classifier 是一个基于 MCP (Model Context Protocol) 的 Solana 链上交易分类微服务。 输入交易哈希,自动分析交易类型(转账、Swap、质押、NFT、DeFi 等),生成合规对账和税务分类草稿, 输出 CSV(兼容 TurboTax / CoinTracker)和 JSON 双格式。前 100 次免费,之后 $0.005 USDC/次(x402 协议,Base 链)。
A production-ready MCP microservice that classifies Solana on-chain transactions for tax reporting and compliance. Feed it a transaction hash, get back a structured classification with tax category, compliance flags, and an exportable CSV report.
Input: 5wHu...3xKq (Solana tx signature)
Output: { type: "swap", tax_category: "capital_gain", usd_value_estimate: 1243.50, ... }
+ CSV download (TurboTax / CoinTracker compatible)
Features
- 7 transaction types:
transfer,swap,stake,nft_trade,defi_interaction,token_mint,unknown - 7 tax categories:
income,capital_gain,capital_loss,gift,self_transfer,fee,not_taxable - IRS-aligned: Notice 2014-21, Rev. Rul. 2023-14 (staking rewards)
- Compliance flags: large transfers (>$10k), DEX interactions, NFT trades, staking rewards, airdrops
- CSV exports: Full audit, CoinTracker format, TurboTax (Form 8949-compatible)
- MCP-native: JSON-RPC 2.0 over HTTP — works with Claude, GPT, Cursor, and any MCP client
- Freemium: First 100 calls free; paid via x402 (USDC on Base)
- Demo fallback: If RPC is unreachable, returns synthetic data clearly marked
demo_mode: true
Quick Start
1. MCP Configuration (Claude Desktop / Cursor)
{
"mcpServers": {
"tunapay-tx-classifier": {
"url": "https://tunapay-tx-classifier.fly.dev/mcp"
}
}
}
Then ask your AI assistant:
"Classify Solana transaction 5wHuVGNbNEW9kSNYDhR9e5oU2F7CcgMH3eTJtpNR9oP"
2. REST API
curl -X POST https://tunapay-tx-classifier.fly.dev/api/v1/classify \
-H "Content-Type: application/json" \
-d '{"tx_hash": "5wHuVGNbNEW9kSNYDhR9e5oU2F7CcgMH3eTJtpNR9oP"}'
Deployment
fly launch --name tunapay-tx-classifier --region sjc
fly secrets set WALLET_ADDRESS=0xYourBaseChainAddress
fly secrets set ADMIN_API_KEY=$(python3 -c "import secrets; print(secrets.token_hex(32))")
fly deploy
License
MIT
Built by TaishanDigital | Powered by TunaPay
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.