MonadKit MCP
Turns Base44's AI builder into a Monad web3 app builder, enabling anyone to vibecode consumer crypto apps (invisible wallets, gasless USDC payments) by describing them in English.
README
⚡ MonadKit MCP
One MCP URL that turns Base44's AI builder into a Monad web3 app builder — so anyone can vibecode a consumer crypto app (invisible wallets, gasless USDC payments) by describing it in English.
Base built an MCP for agents to transact. This is the MCP that lets anyone build — vibecode a consumer crypto app on Monad in one prompt.
How it works
- Next.js (App Router) +
mcp-handler+zod, Streamable HTTP transport. - Endpoint:
https://<project>.vercel.app/api/mcp - Auth: none — every tool is read-only codegen/config. No keys, no funds, no signing.
Tools
| Tool | What it returns |
|---|---|
get_monad_playbook |
Live MONSKILLS guidance fetched from GitHub at request time (cached per instance, hardcoded fallback if GitHub blips). Topics: scaffold, wallet-integration, addresses, wallet, indexer, why-monad — plus aliases like frontend, payments, deploy. MIT, attribution included. |
get_monad_config |
Canonical Monad Testnet config: chainId 10143, RPC https://testnet-rpc.monad.xyz, explorer, faucet, MON (18 dec), testnet USDC. |
scaffold_monad_feature |
Paste-ready plain-React code: wallet_login (Privy embedded wallet, email login) and sponsored_payment (Kernel smart account + Pimlico paymaster, gasless USDC, batched calls). Each includes a SETUP CHECKLIST. |
get_example_project |
bill_split (entity schema + screens + wiring map for Base44) and official_templates (Monad docs template catalog with runtime tags). |
Deploy
npm install
vercel deploy --prod
MCP endpoint is <deployment-url>/api/mcp (SSE fallback at /api/sse).
Connect to Base44
Settings → MCP connections → Add custom MCP → name MonadKit, URL https://<project>.vercel.app/api/mcp, Auth: Not required.
Demo prompt
"Use the MonadKit MCP to build an app where roommates split rent and each pays their share on Monad."
Local smoke test
npm run build && npm start
curl -s -X POST http://localhost:3000/api/mcp \
-H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
Attribution
get_monad_playbook serves content from MONSKILLS (repo), MIT License © Harpalsinh Jadeja.
Roadmap (not built — by design)
x402 paid endpoints (Monad facilitator), onramp/offramp scaffolds, contract deploy tool, more example apps (tip jar, savings circle), full MONSKILLS knowledge base, mainnet config.
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.