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/Hlobo-dev/tengu-mcpWrote 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/hlobo-dev/tengu-mcp/tengu-firm)<a href="https://agentmods.dev/mcp/hlobo-dev/tengu-mcp/tengu-firm"><img src="https://agentmods.dev/badge/mcp/hlobo-dev/tengu-mcp/tengu-firm/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/hlobo-dev/tengu-mcp/tengu-firm"><img src="https://agentmods.dev/badge/mcp/hlobo-dev/tengu-mcp/tengu-firm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
tengu-firm 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 10d 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
{
"tengu-firm": {
"url": "https://firm.tengu.co/mcp",
"type": "streamable-http"
}
}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.
- 10d ago First seen · 6 lines scan A 9b42a4b94edb
tengu-firm is an MCP server published in the GitHub repository Hlobo-dev/tengu-mcp (0 stars, last pushed 29d 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
tradingview-mcp
MCP server "tradingview-mcp" as configured in moeuu/tradingview-mcp. Runs locally from the @moeuu/tradingview-mcp npm package.
hitl-finance-mcp
MCP server for market data, macro calendar, SEC filings and risk tooling, with human-approved order execution. Runs locally from the hitl-finance-mcp Python package. Needs 11 environment variables to run.
agentfeed-algo
Cross-exchange liquidation tape, paid per call in USDC on Algorand. Free catalog, no key needed. Runs locally from the @seekdaseek/agentfeed-algo npm package. Needs 3 environment variables to run.
price-data-mcp
An MCP server that gives AI agents live market prices and candles. Data only, no trading advice. Runs locally from the hyperliquid-price-mcp Python package.
market-data-toolkit-mcp
17 market-data tools for AI agents: eBay sold prices, company KYC, SEC filings, patents, auctions. Remote server at mcp.apify.com.
nordnet-mcp
MCP server "nordnet-mcp" as configured in luimu64/nordnet-mcp. Runs locally from the nordnet-mcp Python package.