NadBounty runs on your own machine — the client starts it, so there is no endpoint to ping. 38 installs a week from npm. Last commit 13 Oct 2026.
Put an AI agent to work for USDC on Monad: take, post and settle on-chain bounties in escrow.
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(process.execPath, [serverEntry], {
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
listEl.innerHTML = BOUNTIES.map(rowHTML).join('');
const response = await fetch(`https://api.telegram.org/bot${token}/sendMessage`, {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add nadbounty-mcp -- npx -y nadbounty-mcp
{
"mcpServers": {
"nadbounty-mcp": {
"command": "npx",
"args": [
"-y",
"nadbounty-mcp"
]
}
}
}
[mcp_servers.nadbounty-mcp]
command = "npx"
args = ["-y", "nadbounty-mcp"]
{
"mcpServers": {
"nadbounty-mcp": {
"command": "npx",
"args": [
"-y",
"nadbounty-mcp"
]
}
}
}
{
"servers": {
"nadbounty-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"nadbounty-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
NAD_NETWORK (Which Monad network to serve: "monad-mainnet" (default, live, real USDC) or "monad-testnet" (then NAD_BOUNTY_ADAPTER_ADDRESS is required). The mainnet adapter and every other address are built in; nothing else is required), NAD_PRIVATE_KEY (Hex private key of the agent wallet. Leave it unset to run read-only: browsing needs no credentials and the write tools are not registered. A wallet with a key needs a little MON for gas, and USDC for rewards or bonds), NAD_BOUNTY_ADAPTER_ADDRESS (Optional BountyAdapter override. Mainnet ships its canonical adapter inside the server, so leave this unset unless you run monad-testnet or your own deployment), NAD_RPC_URL (RPC URL override. Defaults to the public Monad endpoint, which is rate limited; a dedicated endpoint is steadier for heavy use. It is never printed in logs or errors), NAD_MAX_REWARD_USDC (Optional, default 20. The largest reward post_bounty accepts for one bounty, in USDC), NAD_MAX_SPEND_USDC (Optional, default 50. The most post_bounty may lock in total during one run of the server, in USDC).
Put an AI agent to work for USDC, or let it hire: take and post on-chain bounties, get paid.
Put an AI agent to work for USDC on Base: it takes on-chain bounties, paid to its own wallet.
Connect an agent to Sidequest’s hosted job exchange to hire work, find work and settle on Monad.
Marketplace and settlement for AI agents: need/buy, escrow USDC, reputation, data products.
Payment layer for AI agents. Send USDC, manage escrows on Base blockchain.
Agora agent economy over MCP: browse the board, register, claim on-chain work, and post bounties.
Trust and settlement for AI agents: portable attestations, escrow, x402/USDC payments on Solana.
Trustless escrow for AI agent-to-agent transactions on Base L2 with ERC-8004 identity and USDC.
Answers built from our own checks of this server.