How are accounts managed?
Accounts are generated and managed locally using the Nerve SDK; private keys never leave your environment (non-custodial).
@NerveNetwork
基本信息
Nerve blockchain JSON-RPC & REST MCP server for AI agents. Query NVT balances, validate addresses, get transaction history, and swap tokens via NerveSwap DEX. No gas fees on Nerve network. No private key required. npm: nerve-rpc-mcp
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"nerve-rpc": {
"command": "npx",
"args": [
"-y",
"nerve-rpc-mcp"
]
}
}
}Get Nerve chain info (chainId, assetId, symbol, addressPrefix, consensus assets, etc.)
Get the latest main chain block height for a chain
Get the latest block header (hash, height, txCount, packingAddress, etc.)
Validate if a Nerve address is correct for the given chain
Query account balance for a specific asset (chainId, assetChainId, assetId, address)
Query balance list for an address and optional asset IDs
Get block (header + transactions) by block height
Get block (header + transactions) by block hash
Get block header only by height
Get transaction by transaction hash
Get list of consensus nodes (agents) for the chain
Get delegation list for a consensus node (by agent creation tx hash)
Call any Nerve JSON-RPC method by name with params array. Use for methods not covered by dedicated tools (e.g. getRandomSeedByCount, getProposalInfo, swap/farm APIs).
Call Nerve REST API by path. Method GET by default; pass body for POST. Base URL is from NERVE_API_BASE_URL (default https://api.nerve.network). Example paths: api/info, api/block/header/height/1000, api/tx/{hash}
Nerve RPC MCP is an MCP server that exposes Nerve blockchain JSON-RPC and REST endpoints as tools for AI agents. It is part of the Nerve Agent payment framework, enabling AI agents to receive, pay, swap, and query balances on the Nerve network. The protocol is decentralized, accounts are generated and managed locally, and transactions have no gas fees and fast (~2s) confirmation. It also integrates with PayBox for accepting payments from multiple chains (Ethereum, BSC, Polygon, TRON, NULS, NERVE) and receiving USDT on a Nerve address automatically.
Clone the repository, navigate to the nerve rpc mcp directory, run npm install and npm run build. Then add a configuration entry to your MCP client (e.g., Cursor, Claude Desktop) specifying the command as node with args pointing to the built dist/index.js and the environment variable NERVE_API_BASE_URL set to https://api.nerve.network. After publishing to npm, a simpler npx configuration can be used.
Accounts are generated and managed locally using the Nerve SDK; private keys never leave your environment (non-custodial).
No. The server connects to the public Nerve API (`api.nerve.network`) via the `NERVE_API_BASE_URL` environment variable.
Nerve RPC MCP exposes the same functionality as MCP tools, making it directly usable by AI agents and MCP-compatible clients (e.g., Cursor, Claude Desktop) without custom integration code.
No gas fees are charged on Nerve; confirmation is fast (~2 seconds), making it suitable for high-frequency AI payments.
PayBox supports payments from Ethereum, BSC, Polygon, TRON, NULS, and NERVE, with the received USDT automatically appearing on your Nerve address.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

GAIP checks the public declarations of AI agents and MCP servers, watches them for change, witnesses what a delegated call returned and keeps verifiable receipts. Free, read-only, no account or API key. Every result sta

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation
评论