Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add mcp/nirholas/three.ws/agentcore-payments-mcpgit clone --depth 1 https://github.com/nirholas/three.wsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/nirholas/three.ws/agentcore-payments-mcp)<a href="https://agentmods.dev/mcp/nirholas/three.ws/agentcore-payments-mcp"><img src="https://agentmods.dev/badge/mcp/nirholas/three.ws/agentcore-payments-mcp.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
agentcore-payments-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"agentcore-payments-mcp": {
"command": "npx",
"args": [
"-y",
"@three-ws/agentcore-payments-mcp"
],
"env": {
"THREE_WS_SESSION": "",
"PAYMENT_SESSION_TOKEN": "",
"THREE_WS_BASE": "https://three.ws",
"THREE_WS_TIMEOUT_MS": "30000"
}
}
}What else server.json configures
This page is one entry in a file that holds 45. Installing the file brings all of them; each is measured and scanned on its own page.
- MCP server 3D-AI-Agent-Avatar A not measured
- MCP server 3d-agent-mcp A not measured
- MCP server activity-mcp A not measured
- MCP server agenc-mcp A not measured
- MCP server agent-sniper A not measured
- MCP server agora-mcp A not measured
- MCP server alerts-mcp A not measured
- MCP server alibaba-cloud A not measured
- MCP server assistant-widget A not measured
- MCP server audio-mcp A not measured
- MCP server autopilot-mcp A not measured
- MCP server billing-mcp A not measured
- MCP server brain-mcp A not measured
- MCP server clash-mcp A not measured
- MCP server concierge-mcp A not measured
- MCP server copy-mcp A not measured
- MCP server ibm-watsonx A not measured
- MCP server ibm-x402-mcp A not measured
- MCP server ibm-x402-mcp-remote A not measured
- MCP server intel-mcp A not measured
- MCP server kol-mcp A not measured
- MCP server loom-mcp A not measured
- MCP server marketplace-mcp A not measured
- MCP server metaplex-agent A not measured
- MCP server naming-mcp A not measured
- MCP server notifications-mcp A not measured
- MCP server portfolio-mcp A not measured
- MCP server provenance-mcp A not measured
- MCP server pumpfun-solana-mcp A not measured
- MCP server scene-mcp A not measured
- MCP server signals-mcp A not measured
- MCP server three-token-mcp A not measured
- MCP server three.ws A not measured
- MCP server threews-3d-studio A not measured
- MCP server threews-3d-studio-free A not measured
- MCP server threews-agent A not measured
- MCP server threews-avatar A not measured
- MCP server threews-pumpfun A not measured
- MCP server threews-x402-bazaar A not measured
- MCP server tutor-mcp A not measured
- MCP server vanity-mcp A not measured
- MCP server vision-mcp A not measured
- MCP server x402-bridge A not measured
- MCP server x402-mcp A not measured
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 15 lines scan A f13ab4a48007
agentcore-payments-mcp is an MCP server published in the GitHub repository nirholas/three.ws (110 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
maya-mcp
MCP server for controlling Autodesk Maya via commandPort. Runs locally from the maya-mcp Python package.
defiguard-mcp
DeFiGuard MCP Server - DeFi protocol risk analysis tools for AI coding agents. Analyze token co... Runs locally from the defiguard-mcp npm package.
xrpl-referee
Trust and payment layer for the agentic economy on the XRP Ledger. Remote server at xrpl-referee.onrender.com.
defi-agents
General Agent Index and library of specialized AI agents for general use, DeFi, portfolio management, yield optimization, trading, and blockchain automation. Supports linting, automated translation, and CI auto-build for seamless plugin discovery via inde. Runs locally from the @nirholas/ai-agents-library npm package.
monad-mcp
Monad blockchain gateway for AI agents: balances, transfers, swaps, DeFi, with Privy signing. Runs locally from the monad-mcp npm package. Needs 3 environment variables to run.
bitcoin-mcp
MCP server for Bitcoin — 49 tools for AI agents to save money on fees. Zero config, works out of the box. Runs locally from the bitcoin-mcp Python package.