AppsAI
About
Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB
Details
- Author
- appsai-inc
- Categories
- Developer Tools, Other, Infrastructure
Jump to
Setup
Install AppsAI in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/appsai-inc/mcp-server
Follow the installation instructions in the repository README, then restart your MCP client.
- Create and manage full-stack projects— Ask your assistant to scaffold a new Next.js app withproject_CREATE_APPor list existing projects withproject_LIST_APPS.
- Deploy frontends and backends— Trigger deployments viasystem_DEPLOY_FRONTEND,system_DEPLOY_BACKEND, orsystem_DEPLOY_ALLand check deployment status withsystem_GET_ENVIRONMENT_STATUS.
- Manage billing and credits— Check your subscription plan withbilling_GET_CURRENT_PLAN, view your credit balance, or add funds to your account.
- Publish and browse marketplace templates— Usemarketplace_PUBLISH_TEMPLATEto share a project ormarketplace_FORK_TEMPLATEto copy one into your workspace.
- Configure custom domains— Check subdomain availability, assign a custom domain, and verify DNS setup using the domain management tools.
- Invite collaborators and set permissions— Add team members to a project withteam_INVITE_COLLABORATORand adjust their access level.
Build and deploy full-stack apps with AI. This MCP server connects Claude Code, Cursor, Windsurf, and other AI tools to your AppsAI projects.
- Frontend:Next.js with React, Tailwind CSS, and shadcn/ui
- Backend:Parse Server, Express, Fastify, Hono, Supabase Edge Functions, Firebase Cloud Functions, Serverless Framework, or custom
- Database:MongoDB Atlas (managed)
- Infrastructure:AWS (S3, CloudFormation, EC2, Lambda, and more)
claude mcp add appsai -e APPSAI_API_KEY=your_key -- npx -y @appsai/mcp-server
{ "mcpServers": { "appsai": { "command": "npx", "args": ["-y", "@appsai/mcp-server"], "env": { "APPSAI_API_KEY": "your_key" } } } }
- Command:npx -y @appsai/mcp-server
- Environment:APPSAI_API_KEY=your_key
- Sign up atappsai.com
- Go toSettings > Billing > API Keys
- ClickCreate API Key
- Copy the key (shown once)
AI agents can register and obtain API keys programmatically using wallet-based authentication:
import requests from eth_account import Account from eth_account.messages import encode_defunct # Agent's wallet private_key = "0x..." account = Account.from_key(private_key) BASE_URL = "https://internal.appsai.com/server/functions" HEADERS = {"Content-Type": "application/json", "X-Parse-Application-Id": "appsai"} # 1. Get nonce nonce_data = requests.post(f"{BASE_URL}/getAgentAuthNonce", headers=HEADERS, json={}).json()["result"] # 2. Sign the message signed = account.sign_message(encode_defunct(text=nonce_data["message"])) # 3. Register and get API key result = requests.post(f"{BASE_URL}/registerAgentWallet", headers=HEADERS, json={ "walletAddress": account.address, "signature": signed.signature.hex(), "nonce": nonce_data["nonce"] }).json()["result"] api_key = result["apiKey"] # Use this with MCP
Agents can pay for credits using USDC on supported chains (Ethereum, Base, Arbitrum, Polygon):
# 1. Get payment info info = requests.post(f"{BASE_URL}/getCryptoPaymentInfo", headers=HEADERS, json={}).json()["result"] receiving_wallet = info["receivingWallet"] # 2. Send USDC to receiving_wallet (via your preferred method) # 3. Verify transaction and add credits result = requests.post(f"{BASE_URL}/addFundsCrypto", headers=HEADERS, json={ "walletAddress": account.address, "txHash": "0xYOUR_TX_HASH", "chainId": 8453 # Base }).json()["result"] print(f"Credits added: {result['creditsAdded']}")
For detailed API documentation, seeAgent API Docs.
"List my apps" → project_LIST_APPS "Create a new Next.js app" → project_CREATE_APP "Show the file tree for project abc123" → canvas_LIST_FILES "Deploy the frontend" → system_DEPLOY_FRONTEND "Add an MCP server to my project" → system_ADD_MCP_SERVER "Check my current plan" → billing_GET_CURRENT_PLAN "Publish my project to the marketplace" → marketplace_PUBLISH_TEMPLATE "Add a custom domain" → domain_ADD_CUSTOM_DOMAIN "Invite john@example.com to my project" → team_INVITE_COLLABORATOR
AppsAI projects can connect to external MCP servers, giving your AI agents access to additional tools:
"Add the Stripe MCP server to my project" → system_ADD_MCP_SERVER with serverUrl and serverLabel "List my configured MCP servers" → system_LIST_MCP_SERVERS "Disable the Stripe MCP server" → system_UPDATE_MCP_SERVER with enabled: false
Once configured, AI agents in your AppsAI project can use tools from connected MCP servers.
The server provides project context as MCP resources:
- appsai://projects- List of your projects
- appsai://project/{id}- Project details and file structure
Built-in prompts to build full applications:
- build-youtube- Build a YouTube clone with video uploads and comments
- build-slack- Build a Slack clone with real-time messaging
- build-twitter- Build a Twitter/X clone with posts and follows
- connect-apps- Connect two AppsAI projects together
- Node.js 18+
- AppsAI account with credits
- API key from Settings > Billing
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
The official developer experience MCP Server for Amazon DynamoDB. This server provides DynamoDB expert design guidance and data modeling assistance.
Provides an offline AWS CDK API reference.
Get prescriptive CDK advice, explain CDK Nag rules, check suppressions, generate Bedrock Agent schemas, and discover AWS Solutions Constructs patterns.
All Azure MCP tools in a single server. The Azure MCP Server implements the MCP specification to create a seamless connection between AI agents and Azure services. Azure MCP Server can be used alone or with the GitHub Copilot for Azure extension in VS Code.
Run code in secure sandboxes hosted by E2B
Tool platform by IBM to build, test and deploy tools for any data source
The Railway MCP Server enables natural language interaction with your Railway projects and infrastructure. Ask your IDE or AI assistant to create projects, deploy templates, manage environments, pull variables, redeploy services, and more.
The Shipyard CLI provides an MCP server for agents to manage Shipyard environments directly: by pulling logs, comparing branches, running tests, and stopping/starting environments..
Secure virtual machines for agents hosted by Superserve
HashiCorp Terraform MCP server for Infrastructure as Code workflows, including provider and module discovery through the Terraform Registry.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
