DAS MCP Server on Cloudflare Workers
About
A Cloudflare Worker MCP server that integrates with the Helius API to provide asset search tools
Details
- Author
- pratikbuilds
- Downloads
- 332
- Categories
- Cloud Service
Jump to
- Cloudflare Worker MCP server for serverless deployment
- Integrates with Helius API for asset search
- Secure environment variable handling (no secrets in code)
- Ready for Cloudflare AI Playground and Claude Desktop integration
- Easy to extend with custom MCP tools
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
DAS MCP Server on Cloudflare WorkersCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Set the required HELIUS_API_KEY environment variable either in a local .dev.vars file for development or in the Cloudflare Dashboard for production. Deploy using the provided "Deploy to Workers" button or via the CLI template npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless. Connect MCP clients by pointing them to the SSE endpoint (e.g., remote-mcp-server-authless.<your-account>.workers.dev/sse).
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"das mcp server on cloudflare workers": {
"assets-mcp": {
"command": "npx",
"args": [
"wrangler",
"dev"
]
}
}
}
}McpServers
{
"assets-mcp": {
"command": "npx",
"args": [
"wrangler",
"dev"
]
}
}DAS MCP Server on Cloudflare Workers
This project is a Cloudflare Worker that runs a Model Context Protocol (MCP) server, integrating with the Helius API to provide asset search and related tools. It is designed for easy deployment and extension, and uses environment variables for secure API key management.
Features
- Cloudflare Worker MCP server
- Integrates with Helius API (requires HELIUS_API_KEY)
- Secure environment variable handling (no secrets in code or repo)
- Ready for Cloudflare AI Playground and Claude Desktop integration
Environment Variables
Required:
- HELIUS_API_KEY — Your Helius API key (get from https://helius.dev)
Local Development
1. Create a .dev.vars file in the project root:
HELIUS_API_KEY=your-helius-api-key
2. Add
.dev.vars to .gitignore (already done if using template).3. Run locally with:
npx wrangler dev
Cloudflare Deployment
1. Go to your Worker in the Cloudflare Dashboard.
2. Under Settings > Variables, add HELIUS_API_KEY with your API key value.
3. Deploy your Worker as usual.
Troubleshooting:
- If you see an error like HELIUS_API_KEY is not set in environment variables, make sure the variable is set in your local .dev.vars or in the Cloudflare dashboard.
Usage
- The Worker exposes endpoints for MCP tools, including asset search via Helius.
- See src/index.ts for tool definitions and extension points.
Get started:
This will deploy your MCP server to a URL like: remote-mcp-server-authless.<your-account>.workers.dev/sse
Alternatively, you can use the command line below to get the remote MCP Server created on your local machine:
npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless
Customizing your MCP Server
To add your own tools to the MCP server, define each tool inside the init() method of src/index.ts using this.server.tool(...).
Connect to Cloudflare AI Playground
You can connect to your MCP server from the Cloudflare AI Playground, which is a remote MCP client:
1. Go to https://playground.ai.cloudflare.com/
2. Enter your deployed MCP server URL (remote-mcp-server-authless.<your-account>.workers.dev/sse)
3. You can now use your MCP tools directly from the playground!
Connect Claude Desktop to your MCP server
You can also connect to your remote MCP server from local MCP clients, by using the mcp-remote proxy.
To connect to your MCP server from Claude Desktop, follow Anthropic's Quickstart and within Claude Desktop go to Settings > Developer > Edit Config.
Update with this configuration:
{
"mcpServers": {
"calculator": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8787/sse" // or remote-mcp-server-authless.your-account.workers.dev/sse
]
}
}
}
Restart Claude and you should see the tools become available.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
