Agenttoll runs on your own machine — the client starts it, so there is no endpoint to ping. 230 installs a week from npm. Last commit 17 Sep 2026.
21 paid data tools plus free quote/budget inspection, with bounded USDC payments on Base.
We read the source, 0 min ago · rules 3dff92dd89df
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.
…e:"amount",type:"uint256"}],outputs:[{type:"bool"}]}]});var Qy,ex=I(()=>{Qy="0x82ad56cb"});var rf,tx,rx,To,zi=I(()=>{rf="0x608060405234801561001057600080fd5b5060405161018e38038061018e83398101604081905261002f91610124565b6000808351602085016000f59050803b61004857600080fd5b60008083516…
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.
result = subprocess.run(args, input=input, stdout=output or subprocess.PIPE,
for path in parent.iterdir():
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 agenttoll -- npx -y agenttoll-mcp
{
"mcpServers": {
"agenttoll": {
"args": [
"-y",
"agenttoll-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.agenttoll]
command = "npx"
args = ["-y", "agenttoll-mcp"]
{
"mcpServers": {
"agenttoll": {
"args": [
"-y",
"agenttoll-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agenttoll": {
"args": [
"-y",
"agenttoll-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AGENT_PRIVATE_KEY (Optional paying-wallet EVM private key; omit for free quote/budget inspection.), AGENTTOLL_URL (API origin (default https://agenttoll.app); custom origins require AGENTTOLL_RECIPIENT.), AGENTTOLL_NETWORK (Payment network: base (default) or base-sepolia. Base data always uses mainnet.), AGENTTOLL_RECIPIENT (Trusted receiving address; required for a custom API origin.), AGENTTOLL_BUDGET_USDC (Finite session USDC budget (default 1); maximum six decimal places.), AGENTTOLL_MAX_PER_CALL_USDC (Optional lower USDC ceiling; registered endpoint prices remain the upper limit.), AGENTTOLL_TIMEOUT_MS (Total quote/sign/retry/body timeout in milliseconds (default 30000; 1–300000).).
The author declared them in the registry entry; get the values from the project itself.
Real-time data feeds for AI agents with USDC micropayments on Base for premium tools.
Secure USDC payments for AI agents on Base blockchain with budget controls and instant settlement.
33 pay-per-call market and news data tools over MCP with free discovery and x402 payments.
Crypto MCP with 21 tools for market data, DeFi, analytics, and sentiment. Post-paid USDC billing.
Accountless public-source, SEC Form D and OFAC tools with x402 USDC payment on Base.
Read-only payment-boundary preflights plus an unsubmitted public quote-request draft tool.
Pay-per-call data tools for AI agents: crypto signal, web reader, SEO audit. x402 USDC on Base.
AI agent-to-agent SLA agreements on Base with insurance, reputation, and x402 payments.
Answers built from our own checks of this server.