How do I get swap transaction data?
Call the `swap_tokens` tool with required parameters (chainId, tokenIn, tokenOut, amountIn, sender). It returns the calldata and other transaction details.
@Swap-API
基本情報
Free token swaps for AI agents. No API keys. Returns executable transaction calldata for 40+ EVM chains.
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": {
"swapapi": {
"command": "npx",
"args": [
"@swapapi/mcp"
]
}
}
}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。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
Swap Api is a Model Context Protocol (MCP) server that provides AI agents with executable token swap calldata for any EVM chain. It is designed for developers building AI‑powered trading or DeFi assistants.
Install the package globally with npm install -g @swapapi/mcp or run it on the fly with npx @swapapi/mcp. Configure the server in any MCP‑compatible client (e.g., Claude Desktop, Cursor) using the command npx @swapapi/mcp. The server exposes a single tool, swap_tokens, which accepts parameters such as chain ID, token addresses, amount, sender address, and optional slippage.
swap_tokens for swap calldataCall the `swap_tokens` tool with required parameters (chainId, tokenIn, tokenOut, amountIn, sender). It returns the calldata and other transaction details.
The README explicitly lists chain ID 1 (Ethereum), 8453 (Base), and 42161 (Arbitrum), and states “etc.” implying additional EVM chains.
Check ERC‑20 approval for non‑native tokens, verify sender balance, estimate gas with a 20% buffer, simulate the transaction with `eth_call`, and submit within 30 seconds of fetching the quote.
No, the README does not mention any authentication or API key requirement for the MCP server.
Use `0xEeeeeEeeeEeEeeEeEeEeeEEEeeeeEeeeeeeeEEeE` as the token address for native tokens (ETH, MATIC, etc.).

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Agent-Native Terminal

Real UI references for AI coding agents: 500,000+ real screens, 15k+ website design systems with a DESIGN.md, and 30k+ UI elements, so your agent builds UI that looks real, not AI slop.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
コメント