Kaspa MCP Server
Enables interaction with Kaspa blockchain nodes via RPC, providing tools for querying node info, block data, addresses, balances, UTXOs, and mempool transactions.
README
Kaspa MCP Server
MCP server for Kaspa blockchain node RPC integration, providing tools to interact with Kaspa nodes via RPC calls.
🚀 Quick Setup
Prerequisites
- For uvx method: Install uv which includes uvx
- For Docker method: Install Docker
- Kaspa RPC endpoint: Access to a Kaspa node RPC (local or remote)
Installation Methods
Choose one of the following methods based on your MCP client:
📱 Claude Desktop
Add to your Claude Desktop configuration file:
Location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Method 1: Using uvx (Recommended)
{
"mcpServers": {
"kaspa": {
"command": "uvx",
"args": ["--from", "/path/to/mcp-kaspa", "kaspa-mcp-server"],
"env": {
"KASPA_RPC_URL": "http://localhost:16110"
}
}
}
}
Method 2: Using Docker
{
"mcpServers": {
"kaspa": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"--env", "KASPA_RPC_URL=http://host.docker.internal:16110",
"ghcr.io/moldis/mcp-kaspa:latest"
]
}
}
}
🖥️ Cursor IDE
Add to your Cursor settings:
- Open Cursor Settings (Cmd/Ctrl + ,)
- Search for "MCP" or go to Extensions → MCP
- Add new server configuration:
Method 1: Using uvx
{
"mcp.servers": {
"kaspa": {
"command": "uvx",
"args": ["--from", "/path/to/mcp-kaspa", "kaspa-mcp-server"],
"env": {
"KASPA_RPC_URL": "http://localhost:16110"
}
}
}
}
Method 2: Using Docker
{
"mcp.servers": {
"kaspa": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"--env", "KASPA_RPC_URL=http://host.docker.internal:16110",
"ghcr.io/moldis/mcp-kaspa:latest"
]
}
}
}
🎯 Qoder IDE
Add this MCP server in Qoder settings:
- Open Qoder Settings (⌘⇧, on macOS or Ctrl+Shift+, on Windows)
- Navigate to MCP section
- Click "Add Server"
Method 1: Using uvx (Recommended)
- Name: Kaspa MCP Server
- Command: uvx
- Arguments:
--from/path/to/mcp-kaspakaspa-mcp-server
- Environment Variables:
KASPA_RPC_URL=http://localhost:16110
Method 2: Using Docker
- Name: Kaspa MCP Server
- Command: docker
- Arguments:
run-i--rm--envKASPA_RPC_URL=http://host.docker.internal:16110ghcr.io/yourusername/mcp-kaspa:latest
Method 3: Direct Python (Fallback)
If uvx doesn't work:
- Name: Kaspa MCP Server
- Command: python3
- Arguments:
-msrc.main
- Environment Variables:
KASPA_RPC_URL=http://localhost:16110
Configuration Notes for All IDEs:
- Replace
/path/to/mcp-kaspawith the actual absolute path to your cloned repository - For Windows paths, use backslashes:
C:\path\to\mcp-kaspa - For Docker: use
host.docker.internalinstead oflocalhostto access host services - Ensure the path points to the directory containing
pyproject.tomlfor uvx method
🐳 Docker Support
Using Pre-built Image from GitHub Container Registry
The easiest way to use the Docker image is to pull it directly from GitHub Container Registry:
# Pull the latest image
docker pull ghcr.io/moldis/mcp-kaspa:latest
# Or pull a specific version
docker pull ghcr.io/moldis/mcp-kaspa:v1.0.0
Run with Docker
# Test with a local Kaspa node
docker run -i --rm --env KASPA_RPC_URL=http://host.docker.internal:16110 ghcr.io/moldis/mcp-kaspa:latest
# Test with a remote Kaspa node
docker run -i --rm --env KASPA_RPC_URL=http://your-kaspa-node:16110 ghcr.io/moldis/mcp-kaspa:latest
Build the Docker Image Locally (Optional)
If you prefer to build the image yourself:
cd /path/to/mcp-kaspa
docker build -t kaspa-mcp-server:latest .
Docker Notes
- Use
host.docker.internalinstead oflocalhostwhen connecting to services on your host machine - The Docker image includes all necessary dependencies
- Perfect for isolated execution environments
- Images are automatically built and published on every tag push via GitHub Actions
🌍 Network Configuration
Kaspa RPC Endpoints
Local Node:
- Default:
http://localhost:16110 - Docker:
http://host.docker.internal:16110
Public Endpoints (examples):
https://kaspa-rpc.example.com
Environment Variables
KASPA_RPC_URL: Kaspa node RPC endpoint (required)DEBUG: Set totruefor verbose logging (optional)
🛠 Available Tools
- get_node_info - Get Kaspa node information and connection status
- get_block_by_hash - Get detailed information about a specific block by its hash
- get_latest_daa - Get the latest DAA (Difficulty Adjustment Algorithm) score
- get_block_dag_info - Get comprehensive BlockDAG information
- validate_address - Validate a Kaspa address format
- get_address_balance - Get balance for a specific Kaspa address
- get_address_utxos - Get UTXOs (Unspent Transaction Outputs) for specific addresses
- get_mempool_transactions - Get mempool transactions for specific addresses
- get_transaction_by_hash_mempool - Get a specific transaction from mempool by hash (mempool only, not blockchain history)
📚 Resources
kaspa://status- Server status and configurationkaspa://docs/examples- Usage examples
📦 Installation
# Clone the repository
git clone https://github.com/moldis/mcp-kaspa.git
cd mcp-kaspa
# Pull pre-built Docker image (recommended)
docker pull ghcr.io/moldis/mcp-kaspa:latest
# OR build Docker image locally (optional)
docker build -t kaspa-mcp-server:latest .
🔍 Troubleshooting
Common Issues
"Broken Pipe" Error:
- ✅ Fixed: The server now includes comprehensive error handling
- ✅ Fixed: Graceful startup process with proper stdio communication
- ✅ Fixed: Connection timeouts and better RPC error handling
"uvx not found":
- Install uv:
curl -LsSf https://astral.sh/uv/install.sh | sh(Unix) orpowershell -c "irm https://astral.sh/uv/install.ps1 | iex"(Windows) - Use Docker method as alternative
- Use direct Python method as fallback
"Cannot connect to Kaspa RPC":
- Verify your Kaspa node is running and accessible
- Check firewall settings
- For Docker: use
host.docker.internalinstead oflocalhost - Server will start but functionality will be limited until RPC is accessible
MCP Client Can't Find Server:
- Ensure the path to mcp-kaspa directory is correct
- For uvx: path should point to directory containing
pyproject.toml - For Docker: ensure image is built with correct tag
- Check MCP client logs for detailed error messages
Verification Steps
-
Test uvx installation:
cd /path/to/mcp-kaspa echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"1.0.0","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}' | uvx --from . kaspa-mcp-server -
Test Docker setup:
docker run -i --rm --env KASPA_RPC_URL=http://localhost:16110 ghcr.io/moldis/mcp-kaspa:latest -
Check server response: Should return a JSON response with
"result":{"protocolVersion":"2025-06-18"...}
📝 Example Usage
Once configured in your MCP client, you can use tools like:
Basic Node Information
get_node_info()
Address Validation
validate_address("kaspa:qpauqsvk7yf9unexwmxsnmg547mhyga37csh0kj53q6xxgl24ydxjsgzthw5j")
Get Latest DAA Score
get_latest_daa()
Get Block Information
get_block_by_hash("block_hash_here")
Check Address Balance
get_address_balance("kaspa:your_address_here")
Get UTXOs
get_address_utxos(["kaspa:address1", "kaspa:address2"])
Get Transaction from Mempool
get_transaction_by_hash_mempool("transaction_hash_here")
📚 Additional Resources
📝 License
MIT License - see LICENSE file for details.
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.