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/mcpdotdirect/evm-mcp-serverWrote 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/mcpdotdirect/evm-mcp-server/evm-mcp-http)<a href="https://agentmods.dev/mcp/mcpdotdirect/evm-mcp-server/evm-mcp-http"><img src="https://agentmods.dev/badge/mcp/mcpdotdirect/evm-mcp-server/evm-mcp-http/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/mcpdotdirect/evm-mcp-server/evm-mcp-http"><img src="https://agentmods.dev/badge/mcp/mcpdotdirect/evm-mcp-server/evm-mcp-http.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
evm-mcp-http 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 yesterday.
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
{
"evm-mcp-http": {
"command": "npx",
"args": [
"-y",
"@mcpdotdirect/evm-mcp-server",
"--http"
]
}
}What else mcp.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- yesterday First seen · 10 lines scan A 2e3b1b1d4bf1
evm-mcp-http is an MCP server published in the GitHub repository mcpdotdirect/evm-mcp-server (379 stars, last pushed yesterday), 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 2026-09-14.
Other mcp servers, from other repositories
nodeflare-mcp
Blockchain JSON-RPC on 23 EVM chains for AI agents - free tier, API key, or x402 pay-per-call. Runs locally from the nodeflare-mcp npm package. Needs 2 environment variables to run.
nodeflare
MCP server for NodeFlare RPC — blockchain data on 23 EVM chains for AI agents. Free public tier, API key, or pay-per-call with x402 (USDC on Base/Polygon/Arbitrum). Runs locally from the nodeflare-mcp npm package.
evmole
Local structured analysis of deployed EVM runtime bytecode. Runs locally from the evmole-mcp npm package.
waiaas
WAIaaS MCP server - Model Context Protocol integration for AI agents. Runs locally from the @waiaas/mcp npm package. Needs 2 environment variables to run.
solmail
Send physical mail with Solana cryptocurrency - AI agents can send real letters worldwide. Runs locally from the solmail-mcp npm package. Needs 4 environment variables to run.
sui-mcp-server
53-tool MCP server for Sui blockchain — wallets, DeFi, Move contracts, staking, SuiNS, analytics. Runs locally from the sui-mcp-server npm package.