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/UniRate-API/unirate-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/unirate-api/unirate-mcp/unirate)<a href="https://agentmods.dev/mcp/unirate-api/unirate-mcp/unirate"><img src="https://agentmods.dev/badge/mcp/unirate-api/unirate-mcp/unirate/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/unirate-api/unirate-mcp/unirate"><img src="https://agentmods.dev/badge/mcp/unirate-api/unirate-mcp/unirate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
unirate 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
{
"unirate": {
"command": "npx",
"args": [
"-y",
"@unirate/mcp"
],
"env": {
"UNIRATE_API_KEY": "your-api-key-here"
}
}
}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 · 12 lines scan A b184ede90af2
unirate is an MCP server published in the GitHub repository UniRate-API/unirate-mcp (0 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
market-intel-mcp
Live & historical FX rates for AI agents, from European Central Bank data. No API keys. Remote server at market.datakoot.com.
xe-mcp
MCP server for the Xe Currency Data API — real-time rates, historical data, and volatility analysis in Claude Code. Runs locally from the xe-mcp npm package.
apogeoapi-mcp
Geographic data API: 250+ countries, 150K+ cities, IP geolocation, 161 live FX rates. Runs locally from the @apogeoapi/mcp npm package. Needs 1 environment variable to run.
llmkit
AI cost tracking: 11 tools for spend, budgets, and Claude Code + Cursor + Cline costs. Runs locally from the @f3d1/llmkit-mcp-server npm package. Needs 2 environment variables to run.
exchange-rates-mcp-server
Convert currencies, get FX rates, and query historical ECB exchange rate data. Runs locally from the @cyanheads/exchange-rates-mcp-server npm package. Needs 4 environment variables to run.
mcp-quipu
Quipu API integration with 18 MCP tools for invoices, expenses, contacts and Spanish VAT reporting. Runs locally from the @nubiia/mcp-quipu npm package. Needs 3 environment variables to run.