Kreato MCP Server
OfficialClick on "Install 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., "@Kreato MCP ServerTip @creator 1 USDC"
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.
Kreato MCP Server
Connect any AI agent (Claude, GPT, custom agents) to Kreato — letting users tip creators, buy digital products, and manage memberships through natural language.
What it does
Once deployed, a user can tell Claude:
"Tip @alexbuilds 5 USDC on Base" "Buy the Web3 Dev Guide from @alexbuilds" "Show me my earnings for the last 30 days" "Find Web3 developers selling courses under $20"
And it just works — on-chain, directly to the creator's wallet.
Quick start
1. Clone and install
git clone https://github.com/kreatospace/kreato-mcp
cd kreato-mcp
npm install2. Configure environment
cp .env.example .envFill in .env:
KREATO_API_URL=https://api.kreato.space/v1
KREATO_API_SECRET=your_server_secret
PORT=3000
MCP_SERVER_URL=https://mcp.kreato.space
OAUTH_CLIENT_ID=your_oauth_client_id
OAUTH_CLIENT_SECRET=your_oauth_client_secret
OAUTH_REDIRECT_URI=https://mcp.kreato.space/oauth/callbackGet your KREATO_API_SECRET and OAuth credentials from the Kreato developer dashboard.
3. Run locally
npm run devServer starts at http://localhost:3000.
4. Test with Claude Desktop (local)
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"kreato": {
"command": "node",
"args": ["/absolute/path/to/kreato-mcp/src/index.js"],
"env": {
"KREATO_API_URL": "https://api.kreato.space/v1",
"KREATO_API_SECRET": "your_secret"
}
}
}
}Restart Claude Desktop and you'll see the Kreato tools available.
Deploy to production
Railway (recommended — one click)
# Install Railway CLI
npm install -g @railway/cli
# Login and deploy
railway login
railway init
railway upSet env vars in the Railway dashboard, then set your custom domain to mcp.kreato.space.
Docker
docker build -t kreato-mcp .
docker run -p 3000:3000 --env-file .env kreato-mcpFly.io
fly launch
fly secrets set KREATO_API_SECRET=xxx OAUTH_CLIENT_SECRET=xxx
fly deployMCP tools reference
Tool | Auth required | Description |
| No | Search creators by keyword, chain, category |
| No | Full profile, products, and membership tiers |
| Yes | Tip a creator in ETH or USDC |
| Yes | Purchase a digital download |
| Yes | Subscribe to or cancel a membership tier |
| Yes | Earnings, top products, supporter stats |
Auth flow
Protected tools trigger an OAuth flow automatically:
Agent calls
send_donationwithout a connected accountMCP server returns
auth_requiredwith a login URLUser clicks the link, logs in on kreato.space, grants permission
User returns to the AI — the agent retries automatically
Submit to Anthropic's MCP directory
Once your server is live and stable, submit it at: https://github.com/modelcontextprotocol/servers
Include:
Server URL:
https://mcp.kreato.space/sseName:
KreatoDescription: "Web3 creator monetization — tip creators, buy digital products, manage memberships in crypto"
Auth type: OAuth 2.0
Project structure
kreato-mcp/
├── src/
│ ├── index.js # Express server + SSE transport
│ ├── tools.js # All MCP tool definitions
│ ├── kreato-client.js # Kreato REST API wrapper
│ └── oauth.js # OAuth 2.0 flow handler
├── .env.example
├── Dockerfile
└── README.mdThis server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kreatospace/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server