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/mahak867/ai-projects-hubWrote 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/mahak867/ai-projects-hub/financial-analyst)<a href="https://agentmods.dev/mcp/mahak867/ai-projects-hub/financial-analyst"><img src="https://agentmods.dev/badge/mcp/mahak867/ai-projects-hub/financial-analyst/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/mahak867/ai-projects-hub/financial-analyst"><img src="https://agentmods.dev/badge/mcp/mahak867/ai-projects-hub/financial-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
financial-analyst 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
{
"financial-analyst": {
"command": "python",
"args": [
"/FULL/PATH/TO/server.py"
],
"env": {
"PYTHONPATH": "/FULL/PATH/TO/project"
}
}
}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 · 11 lines scan A 2bb9361228f4
financial-analyst is an MCP server published in the GitHub repository mahak867/ai-projects-hub (11 stars, last pushed 4mo 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 2026-08-30.
Other mcp servers, from other repositories
openaccountants-mcp
MCP server for OpenAccountants tax skills. Runs locally from the openaccountants-mcp Python package.
stripe
Stripe's hosted MCP server: lets the agent work with customers, products, prices and payment links. Remote server at mcp.stripe.com.
trading212-mcp-server
MCP server for Trading 212 - 32 tools for portfolio management, trading, pies, dividends, and analytics. Works with Claude, ChatGPT, Cursor, and any MCP client. Runs locally from the trading212-mcp-server Python package. Needs 3 environment variables to run.
blackline
MCP server "blackline", hosted remotely at api.blackline.com, as configured in vivy-yi/finance-skills.
vertex-o
MCP server "vertex-o", hosted remotely at {company}.vertexinc.com, as configured in vivy-yi/finance-skills.
bantou
AI bookkeeping agent for Japanese accountants — auto-classifies freee/Yayoi/MF/TKC transactions. Runs locally from the @kansei-link/bantou npm package.