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/michielinksee/bantouWrote 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/michielinksee/bantou/claude-for-jp-accounting-bantou)<a href="https://agentmods.dev/mcp/michielinksee/bantou/claude-for-jp-accounting-bantou"><img src="https://agentmods.dev/badge/mcp/michielinksee/bantou/claude-for-jp-accounting-bantou/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/michielinksee/bantou/claude-for-jp-accounting-bantou"><img src="https://agentmods.dev/badge/mcp/michielinksee/bantou/claude-for-jp-accounting-bantou.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
bantou 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 12d 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
{
"bantou": {
"command": "npx",
"args": [
"-y",
"@kansei-link/bantou@latest"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"FREEE_ACCESS_TOKEN": "${FREEE_ACCESS_TOKEN}",
"FREEE_COMPANY_ID": "${FREEE_COMPANY_ID}"
}
}
}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.
- 12d ago First seen · 14 lines scan A b6d419b75ad7
bantou is an MCP server published in the GitHub repository michielinksee/bantou (2 stars, last pushed 21d 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
buchhaltungsbutler-mcp
MCP server "buchhaltungsbutler-mcp" as configured in ohneben/Buchhaltungsbutler-MCP. Runs in Docker (ghcr.io/ohneben/buchhaltungsbutler-mcp:1.1.1). Needs 6 environment variables to run.
ledger
Exact-decimal double-entry for agents. Call MCP tools; do not do money math in tokens. Runs locally from the @eternal-roman/ledger-mcp npm package.
mcp-fns-calc
A local MCP server for Russian tax calculations and checks of taxpayer status. It uses a hosted API for fiscal-status checks and needs an access token.
bank-statement-converter
MCP server for the MainBook bank-statement conversion API. Runs locally from the mainbook-mcp Python package. Needs 1 environment variable to run.
benethos-lexware-office-mcp
Unofficial MCP server for the Lexware Office accounting API. Runs locally from the benethos-lexware-office-mcp Python package.
freeagent-mcp-server
FreeAgent accounting MCP: bank reconciliation, expenses, mileage claims and receipts. Runs locally from the @oxygenbubbles/freeagent-mcp-server npm package. Needs 7 environment variables to run.