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/bnmbnmai/mcp-proxyWrote 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/bnmbnmai/mcp-proxy/intelligence)<a href="https://agentmods.dev/mcp/bnmbnmai/mcp-proxy/intelligence"><img src="https://agentmods.dev/badge/mcp/bnmbnmai/mcp-proxy/intelligence/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/bnmbnmai/mcp-proxy/intelligence"><img src="https://agentmods.dev/badge/mcp/bnmbnmai/mcp-proxy/intelligence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
intelligence 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 1mo 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
{
"intelligence": {
"command": "npx",
"args": [
"-y",
"@apollo_ai/mcp-proxy"
],
"env": {
"APOLLO_API_URL": ""
}
}
}What else server.json configures
This page is one entry in a file that holds 4. 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.
- 1mo ago First seen · 12 lines scan A 95f53ded3b86
intelligence is an MCP server published in the GitHub repository bnmbnmai/mcp-proxy (2 stars, last pushed today), 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
mcp
MCP server "mcp", hosted remotely at mcp.0xarchive.io, as configured in 0xArchiveIO/0xarchive-mcp.
undertow
Daily editorials, exit costs, depth concentration, tiers, and sealed records. No commodity futures. Remote server at api.seiche.info.
cerebrus-pulse-mcp
MCP server for Cerebrus Pulse — real-time crypto intelligence API for Hyperliquid perpetuals. Runs locally from the cerebrus-pulse-mcp Python package.
eqvps
No-KYC crypto VPS AI agents rent & run over MCP — 57 tools, pay USDC/USDT on Base/Eth/Polygon/Solana. Remote server at mcp.eqvps.com.
x402-api
DeFi data API for AI agents — pay-per-call via x402/USDC on Base. Runs locally from the @x402-api/mcp-server npm package. Needs 1 environment variable to run.
pythia-oracle-mcp
Every smart contract deserves intelligence, not just data. Pythia Oracle MCP server — on-chain calculated indicators via Chainlink. Runs locally from the pythia-oracle-mcp Python package.