nano-currency
Send Nano currency from AI agents/LLMs
claude mcp add --transport stdio kilkelly-nano-currency-mcp-server node nano-currency.js \ --env NANO_RPC_URL="ENTER_YOUR_NANO_RPC_URL" \ --env NANO_PRIVATE_KEY="ENTER_YOUR_NANO_PRIVATE_KEY" \ --env X402_NANO_NETWORK="ENTER_X402_NANO_NETWORK" \ --env RAW_MAX_SEND_AMOUNT="ENTER_RAW_MAX_SEND_AMOUNT" \ --env NANO_MAX_SEND_AMOUNT="ENTER_NANO_MAX_SEND_AMOUNT" \ --env NANO_WORK_GENERATION_URL="ENTER_YOUR_NANO_WORK_GENERATION_URL_OR_LEAVE_EMPTY"
How to use
Nano Currency MCP Server exposes a set of MCP-compatible tools that let AI agents or MCP clients interact with a Nano node. It supports sending Nano or raw units, querying account and block information, and creating x402-compatible payment headers. Tools include raw_send, nano_send, nano_account_info, nano_my_account_info, block_info, and x402_payment_signature_exact_scheme_create. To use the server, configure your MCP client to connect to the server's nano_currency endpoint and provide the required environment variables for the Nano RPC, account keys, and safety limits. The server will enforce limits based on RAW_MAX_SEND_AMOUNT and NANO_MAX_SEND_AMOUNT to prevent large accidental transfers, and it can generate x402 headers for pay-per-resource interactions.
How to install
Prerequisites: Node.js and npm installed on your system. You should have a Git client to clone the repository.
Code installation steps:
- git clone https://github.com/kilkelly/nano-currency-mcp-server.git
- cd nano-currency-mcp-server
- npm install
Configuration steps:
- Create or edit an environment/config file to provide the required NANO_RPC_URL, NANO_WORK_GENERATION_URL (optional), NANO_PRIVATE_KEY, RAW_MAX_SEND_AMOUNT, NANO_MAX_SEND_AMOUNT, and X402_NANO_NETWORK values.
- Adjust any additional settings in your deployment environment as needed.
Run the server:
- Ensure you know the path to the Node.js runtime and the main script (as used in mcp_config, e.g., nano-currency.js).
- Start the server using your preferred process manager or via a direct node command, for example:
# From project root, if the main file is nano-currency.js
node nano-currency.js
If you are using a process manager or container, provide the same environment variables to the process and expose the MCP interface to your MCP clients.
Additional notes
Tips and caveats:
- Always test with small amounts of Nano before enabling higher transfer limits. Use RAW_MAX_SEND_AMOUNT and NANO_MAX_SEND_AMOUNT to cap transfers.
- Ensure NANO_PRIVATE_KEY is kept secure; it should correspond to the account used by nano_send/raw_send and related tools.
- If NANO_WORK_GENERATION_URL is not provided, the server will default to NANO_RPC_URL for work generation.
- The x402 header creation tool (x402_payment_signature_exact_scheme_create) enables programmatic payments in x402 schemes; make sure X402_NANO_NETWORK matches the target network (e.g., nano:mainnet).
- When running in production, consider access controls and rate limits to avoid misuse by automated agents.
- If you rotate keys or endpoints, update the environment variables accordingly and restart the MCP server.
Related MCP Servers
bytebot
Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.
agents
Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.
aser
Aser is a lightweight, self-assembling AI Agent frame.
moling
MoLing is a computer-use and browser-use based MCP server. It is a locally deployed, dependency-free office AI assistant.
agenite
🤖 Build powerful AI agents with TypeScript. Agenite makes it easy to create, compose, and control AI agents with first-class support for tools, streaming, and multi-agent architectures. Switch seamlessly between providers like OpenAI, Anthropic, AWS Bedrock, and Ollama.
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.