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/bitrefill/agentsWrote 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/bitrefill/agents/bitrefill)<a href="https://agentmods.dev/mcp/bitrefill/agents/bitrefill"><img src="https://agentmods.dev/badge/mcp/bitrefill/agents/bitrefill/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/bitrefill/agents/bitrefill"><img src="https://agentmods.dev/badge/mcp/bitrefill/agents/bitrefill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
bitrefill 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 4d 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
{
"bitrefill": {
"type": "http",
"url": "https://api.bitrefill.com/mcp",
"placement": "server"
}
}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.
- 4d ago Changed · +1 lines bbfa4a59c5cf
- 1mo ago First seen · 6 lines scan A 20f45bc837bb
bitrefill is an MCP server published in the GitHub repository bitrefill/agents (27 stars, last pushed 5d 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
stripe
Stripe's hosted MCP server: lets the agent work with customers, products, prices and payment links. Remote server at mcp.stripe.com.
facturahub
MCP server for invoicing, WooCommerce, expenses, POS, inventory, tasks, tax declarations, and business management. 69 AI tools for Claude, ChatGPT, Cursor, and Windsurf. Freelancers, e-commerce, and startups. Runs locally from the facturahub npm package.
mcp-braspag
MCP server for Braspag — Cielo orchestration, token vault (Cartão Protegido), recurrence, split. Runs locally from the @codespar/mcp-braspag npm package. Needs 3 environment variables to run.
mcp-tiny
MCP server for Tiny ERP — products, stock, warehouses, price lists, orders, invoices, AP/AR. Runs locally from the @codespar/mcp-tiny npm package. Needs 1 environment variable to run.
crypto
Crypto token and narrative trend volume over time, with growth signals. Free key at trendsmcp.ai. Remote server at crypto.api.trendsmcp.ai.
cardos-mcp
MCP server for CardOS — issue and manage virtual cards via the Model Context Protocol. Works with Claude, Cursor, Windsurf and any MCP client. Runs locally from the cardos-mcp npm package. Needs 2 environment variables to run.