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/askcal/cal-mcp-serverWrote 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/askcal/cal-mcp-server/cal)<a href="https://agentmods.dev/mcp/askcal/cal-mcp-server/cal"><img src="https://agentmods.dev/badge/mcp/askcal/cal-mcp-server/cal/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/askcal/cal-mcp-server/cal"><img src="https://agentmods.dev/badge/mcp/askcal/cal-mcp-server/cal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cal 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
{
"cal": {
"command": "npx",
"args": [
"-y",
"@askcal/mcp-server"
],
"env": {
"CAL_API_TOKEN": "cal_live_REPLACE_WITH_YOUR_API_KEY_FROM_AUTH_API_KEYS_ENDPOINT"
}
}
}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 b6b9c7f32456
cal is an MCP server published in the GitHub repository askcal/cal-mcp-server (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
tradingview-mcp
Real-time market data, screeners, technical analysis & backtesting for stocks, crypto and forex. Remote server at mcp.cryptosieve.com.
canary
MCP server "canary" as configured in osauer/canary. Launched with https://github.com/osauer/canary/releases/download/v3.9.2/canary-v3.9.2.mcpb.
claude-tradingview-mcp
MCP server "claude-tradingview-mcp" as configured in aidenhecker/claude-tradingview-mcp. Runs locally from the claude-tradingview-mcp Python package.
bitget-agent-mcp
Official Bitget MCP Server for the Unified Trading Account (UTA v3) API. Runs locally from the @bitget-ai/bitget-agent-mcp npm package. Needs 3 environment variables to run.
agentdata-mcp
Verifiable crypto signals, recorded history and always-on monitoring for AI agents via x402 on Base. Remote server at agentdata-api.com.
edgaralert
SEC insider trading alerts, Form 4 signals, 8-K events, and company research via EDGAR Alert API. Runs locally from the @edgaralert/mcp-server npm package. Needs 1 environment variable to run.