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/Pentagonal-ai/pentagonalWrote 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/pentagonal-ai/pentagonal/pentagonal-mcp)<a href="https://agentmods.dev/mcp/pentagonal-ai/pentagonal/pentagonal-mcp"><img src="https://agentmods.dev/badge/mcp/pentagonal-ai/pentagonal/pentagonal-mcp/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/pentagonal-ai/pentagonal/pentagonal-mcp"><img src="https://agentmods.dev/badge/mcp/pentagonal-ai/pentagonal/pentagonal-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pentagonal-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 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
{
"pentagonal-mcp": {
"command": "npx",
"args": [
"-y",
"pentagonal-mcp"
],
"env": {
"PENTAGONAL_API_KEY": ""
}
}
}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 58e7246e254c
pentagonal-mcp is an MCP server published in the GitHub repository Pentagonal-ai/pentagonal (1 stars, last pushed 2mo 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
bug-bounty-intelligence-mcp
AI security scanner for Solidity + free CC0 dataset of Sherlock audit-competition acceptance rates. Remote server at wazir-x402.duckdns.org.
3ilm-mcp
Search 1,032 verified smart contract vulnerability findings from Sherlock audits by pattern. Runs locally from the 3ilm-mcp npm package.
mcp-klever-vm
MCP server for Klever blockchain smart contract development. Runs locally from the @klever/mcp-server npm package.
token-intel
Solana token due-diligence: 3-source fused risk verdict incl. LP-lock depth. $0.01 via x402. Remote server at token-intel-x402.echolonius.deno.net.
infura-mcp
A MCP server for interacting with blockchains via Infura APIs. Runs locally from the infura-mcp npm package.
evm-mcp-http
MCP server for interacting with EVM-compatible blockchains - supports 22 tools and 10 prompts across 60+ networks. Runs locally from the @mcpdotdirect/evm-mcp-server npm package.