SmoothSend MCP Server
This MCP server helps AI assistants integrate SmoothSend's gasless transaction services for Aptos and Avalanche (AVAX) by providing documentation, code snippets, credit estimation, and address lookups.
Get documentation for sections like overview, installation, quickstart, API reference, examples, and billing (Aptos) plus AVAX-specific docs.
Estimate monthly credit costs based on gas usage, gas price, APT price, and transaction volume.
Look up Aptos mainnet token addresses for USDC, USDT, WBTC, USDe, and USD1.
Get AVAX deployed contract addresses (EntryPoint, VerifyingPaymaster, SimpleAccountFactory) and supported tokens for Fuji and mainnet.
Fetch ready-to-use code snippets for patterns like wallet adapter setup, per-function gasless routing, USDC transfers, fee preview, error handling, testnet setup, and AVAX-specific integrations (wagmi, Privy, backend).
Provide direct resource access to documentation pages via URIs for AI assistants to read.
Provides guidance and code snippets for integrating SmoothSend gasless transactions into Next.js applications, including wallet adapter setup and error handling.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@SmoothSend MCP Server show me how to send USDC on Aptos without the user paying for gas"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@smoothsend/mcp
MCP (Model Context Protocol) server for SmoothSend. Enables AI assistants in Cursor, Claude Desktop, Windsurf, and other MCP-compatible tools to help developers integrate gasless transactions on Aptos and Avalanche (AVAX).
What it does
Once configured, AI assistants in your editor can:
Answer questions about the SmoothSend SDK and API — Aptos (fee-payer gasless) and AVAX (ERC-4337 account abstraction)
Generate integration code for any use case, including wagmi, Privy, and backend/Node patterns on AVAX
Estimate monthly credit costs based on your transaction volume
Look up Aptos mainnet token addresses (USDC, USDT, WBTC, USDe, USD1)
Look up AVAX deployed contract addresses (EntryPoint, VerifyingPaymaster, SimpleAccountFactory) and supported tokens, per network (Fuji / mainnet)
Pull up full documentation for any section (installation, quickstart, examples, billing, and the AVAX equivalents)
Related MCP server: mindcore-mcp
Install
npm install -g @smoothsend/mcpOr run directly with npx (no install needed):
npx @smoothsend/mcpConfigure
Cursor
Add to ~/.cursor/mcp.json (or your project's .cursor/mcp.json):
{
"mcpServers": {
"smoothsend": {
"command": "npx",
"args": ["@smoothsend/mcp"]
}
}
}Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"smoothsend": {
"command": "npx",
"args": ["@smoothsend/mcp"]
}
}
}Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"smoothsend": {
"command": "npx",
"args": ["@smoothsend/mcp"]
}
}
}Tools
Tool | Description |
| Get documentation for a section. Aptos: |
| Estimate monthly Aptos credits given |
| Get Aptos mainnet asset address for |
| Get AVAX deployed contract addresses (EntryPoint, VerifyingPaymaster, SimpleAccountFactory) and supported tokens for |
| Get a code snippet. Aptos: |
Resources
Resources are doc pages that AI assistants can read directly:
URI | Content |
| Overview, quick start, pricing (Aptos) |
| Installation guide (Aptos) |
| Step-by-step quickstart (Aptos) |
| Full API reference (Aptos) |
| Real-world code examples (Aptos) |
| Pricing and credit details |
| AVAX overview — ERC-4337, sponsorship modes, how it differs from Aptos |
| Step-by-step AVAX quickstart — wagmi and Privy paths |
| Full AVAX API reference — provider, hooks, |
| Real-world AVAX examples — wagmi, Privy, and backend/Node |
Example prompts
Once configured, try asking your AI assistant:
"How do I add SmoothSend to my Next.js app?"
"Show me how to send USDC without the user needing APT"
"My dApp does ~5000 contract calls per month at 200 gas each. How much will SmoothSend cost?"
"What's the USDC asset address on Aptos mainnet?"
"How do I handle SmoothSend errors when credits run out?"
"How do I sponsor gas for my wagmi dApp on Avalanche?"
"What's the VerifyingPaymaster address on Avalanche Fuji?"
"How do I submit a sponsored AVAX transaction from a backend script?"
"How do I use SmoothSend with a Privy embedded wallet on Avalanche?"
Development
# Install dependencies
npm install
# Build TypeScript
npm run build
# Type check
npm run typecheck
# Run locally
node dist/index.jsLinks
Available Tools
4 toolsestimate_creditsA
Estimate the monthly SmoothSend credit cost for a dApp based on transaction volume and type. Returns per-transaction fee and monthly total.
Inputs: gas_used (required), volume (required), gas_unit_price, apt_price_usd.
get_code_snippetB
Get a ready-to-use code snippet for a specific SmoothSend integration pattern.
Inputs: use_case (required).
get_docsA
Get SmoothSend documentation for a specific topic. Use this to answer questions about installation, integration, API methods, examples, or billing.
Inputs: topic (required).
get_token_addressA
Get the Aptos Mainnet fungible asset address for a supported token (USDC, USDT, WBTC, USDe, USD1). Required when using ScriptComposerClient.
Inputs: symbol (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: cost estimation, code retrieval, documentation access, and token address lookup. An agent can easily differentiate between them based on their specific functions.
All tools follow a consistent verb_noun pattern (estimate_credits, get_code_snippet, get_docs, get_token_address) with 'get' used for three tools and 'estimate' for one, maintaining readability and predictability throughout.
Four tools are reasonable for a SmoothSend integration server, covering key areas like cost, code, docs, and tokens. It's slightly lean but not incomplete, as the tools address core needs without unnecessary bloat.
The tool set covers essential integration tasks: planning (estimate), implementation (code snippet), reference (docs), and configuration (token address). Minor gaps might exist, such as direct API calls or transaction execution, but agents can work around these using the provided tools.
Maintenance
Related MCP Connectors
Verified EVM, Aptos and finance tools for AI agents; gas for 14 chains. Pay per call (x402).
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
API discovery and x402 paid execution via MCP. Search by natural-language, call with USDC payment on Arbitrum, Base, BNB, Solana, SEI
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to resolve smart contract ABIs, read, encode, simulate, and prepare transactions across multiple blockchains via a REST API or MCP server, with no signing required.-
- AlicenseNot gradedqualityDmaintenanceEnables AI-powered chat and DeFi operations (swap, transfer) via MCP-compliant tools, integrating with LLMs for onchain actions.13 npmMIT
- AlicenseNot gradedqualityCmaintenanceProvides 59 pay-per-call AI tools covering crypto prices and audits, market and whale data, LLM chat, image generation, web search/fetch/summarize, and utility services, with automatic x402 USDC-on-Base payments and on-chain receipts. It works with Claude Code/Desktop, Cursor, and other MCP clients without API keys or subscriptions.53 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to perform software development tasks such as codebase analysis, research, planning, requirements and user-story generation, task management, project scaffolding, and multi-step workflow execution. It integrates with MCP-compatible clients like Claude Desktop, Cursor, and Cline AI.42 npmMIT