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/callbk/finlight-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/callbk/finlight-mcp/news)<a href="https://agentmods.dev/mcp/callbk/finlight-mcp/news"><img src="https://agentmods.dev/badge/mcp/callbk/finlight-mcp/news.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
news 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 6d 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
{
"news": {
"command": "npx",
"args": [
"-y",
"finlight-mcp"
],
"env": {}
}
}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.
- 6d ago First seen · 10 lines scan A 3287040701f3
news is an MCP server published in the GitHub repository callbk/finlight-mcp (0 stars, last pushed 20d 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
ibanforge
Pre-payout IBAN screening for AI agents: validation, sanctions, Swiss clearing, risk scoring. Runs locally from the ibanforge-mcp npm package. Needs 2 environment variables to run.
alphai-mcp
AI-enriched financial news for AI agents & trading bots: search, trending, insider, scored 1-10. Remote server at mcp.alphai.io.
mcp
Live AU/NZ bank (CDR) and brokerage data for AI agents, plus management of Redbark syncs and rules. Remote server at mcp.redbark.com.
mcp
MCP server and client for SEC-registered financial advisor data — search, profiles, disclosures status, firm fees. By AdvisorFinder. Runs locally from the advisorfinder-mcp Python package.
market-eyes-live
Free MCP: typed MELANY ratings for any US stock or ETF (11,000+) plus mortgage-rate context. Remote server at marketeyeslive.com.
xendit-mcp
Xendit payment APIs for AI agents. Payment links, payouts, balances, and transactions. Runs locally from the xendit-mcp npm package.