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.
git clone --depth 1 https://github.com/andresdefi/zerodustWrote 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/andresdefi/zerodust/mcp-server-zerodust)<a href="https://agentmods.dev/mcp/andresdefi/zerodust/mcp-server-zerodust"><img src="https://agentmods.dev/badge/mcp/andresdefi/zerodust/mcp-server-zerodust.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
zerodust 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 7d 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
{
"zerodust": {
"command": "npx",
"args": [
"-y",
"@zerodust/mcp-server"
],
"env": {
"ZERODUST_API_URL": "",
"ZERODUST_API_KEY": "",
"ZERODUST_ALLOW_EXECUTE": "",
"ZERODUST_SIGNER_MODULE": "",
"ZERODUST_KEYSTORE_FILE": "",
"ZERODUST_KEYSTORE_PASSWORD_FILE": "",
"ZERODUST_KEYSTORE_PASSWORD": "",
"ZERODUST_PRIVATE_KEY_FILE": "",
"ZERODUST_PRIVATE_KEY": "",
"ZERODUST_ALLOWED_DESTINATIONS": ""
}
}
}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.
- 7d ago First seen · 21 lines scan A c0ba72b51153
zerodust is an MCP server published in the GitHub repository andresdefi/zerodust (2 stars, last pushed 1mo ago), licensed MIT. 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 2026-08-31.
Other mcp servers, from other repositories
robyn
Gasless cross-chain for AI agents: 25 nodes incl. Solana & native Bitcoin. One signature, no gas. Runs locally from the anygas-mcp npm package. Needs 2 environment variables to run.
ugf-mcp
MCP server for Universal Gas Framework. Lets any AI agent (Claude Desktop, Codex, Gemini, Cursor, etc.) send transactions across EVM, Solana, and Sui WITHOUT holding the destination chain's native gas. Pay with stablecoins (USDC, EURC) or any native EVM c. Runs locally from the @tychilabs/ugf-mcp npm package.
robinx-mcp
Robinhood Chain (4663) caller accuracy + token intel, graded vs real price since genesis. x402-paid. Runs locally from the robinx-mcp npm package. Needs 1 environment variable to run.
openchainbench
Live, neutral benchmarks for public RPC latency, oracles, bridges, perp DEX, and prediction markets. Remote server at openchainbench.com.
solana-dev
MCP server "solana-dev", hosted remotely at mcp.solana.com, as configured in GeckoVision/gecko-surf.
suwappu
Cross-chain DEX for AI agents. Swap tokens across 7+ chains. Runs locally from the @suwappu/mcp-server npm package. Needs 1 environment variable to run.