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/HMAKT99/ErabiWrote 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/hmakt99/erabi/mcp-erabi)<a href="https://agentmods.dev/mcp/hmakt99/erabi/mcp-erabi"><img src="https://agentmods.dev/badge/mcp/hmakt99/erabi/mcp-erabi/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/hmakt99/erabi/mcp-erabi"><img src="https://agentmods.dev/badge/mcp/hmakt99/erabi/mcp-erabi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
erabi 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 9d 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
{
"erabi": {
"command": "npx",
"args": [
"-y",
"erabi-mcp"
],
"env": {
"ERABI_REGISTRY_URL": "",
"ERABI_EXCHANGE_URL": "",
"ERABI_ATTRIBUTION_URL": "",
"ERABI_REPUTATION_URL": "",
"ERABI_KEY_DIR": ""
}
}
}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.
- 9d ago First seen · 16 lines scan A 28be891b0358
erabi is an MCP server published in the GitHub repository HMAKT99/Erabi (1 stars, last pushed 1mo ago), 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 2026-08-31.
Other mcp servers, from other repositories
magpie-mcp
Agent-native lending on Solana via x402: borrow against tokens, arm in-vault TP/SL, repay. Runs locally from the @magpieloans/magpie-mcp npm package.
x402-payment-safety
Authorize x402 payments before signing with request-bound, signed safety decisions. Remote server at agent-guild-5d5r.onrender.com.
cedulon
Policy-gated agent spend with signed receipts and rail-extract audit. Runs locally from the @cedulon/mcp-server npm package. Needs 4 environment variables to run.
mcp
Credit scores for AI agents. Underwrite an unknown counterparty before extending credit. Remote server at solvscore.com.
fidacy
You're the one in charge of your AI agent. But it doesn't know your limits. Authorize, deny, release and record on every consequential action, as an MCP server. Non-custodial. Runs locally from the @fidacy/mcp npm package.
datafood-mcp
DataFood: 16 data sources (crypto/DeFi/security/news/finance) via one MCP. Bundles save 92%. Remote server at toughlovesec.win.