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/AccountantInc/mcp-kikoWrote 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/accountantinc/mcp-kiko/kikobooks-mcp-server)<a href="https://agentmods.dev/mcp/accountantinc/mcp-kiko/kikobooks-mcp-server"><img src="https://agentmods.dev/badge/mcp/accountantinc/mcp-kiko/kikobooks-mcp-server/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/accountantinc/mcp-kiko/kikobooks-mcp-server"><img src="https://agentmods.dev/badge/mcp/accountantinc/mcp-kiko/kikobooks-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kikobooks-mcp-server 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
{ "kikobooks-mcp-server": { "command": "npx", "args": [ "-y", "@kikobooks/kikobooks-mcp-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.
- 10d ago First seen · 9 lines scan A a5f44587c63d
kikobooks-mcp-server is an MCP server published in the GitHub repository AccountantInc/mcp-kiko (0 stars, last pushed 6mo 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.
qbo-mcp
MCP server "qbo-mcp" as configured in WYRE-AI/qbo-mcp. Runs in Docker (ghcr.io/wyre-ai/qbo-mcp:v1.6.5). Needs 8 environment variables to run.
xero-mcp
MCP server "xero-mcp" as configured in WYRE-AI/xero-mcp. Runs in Docker (ghcr.io/wyre-ai/xero-mcp:v1.5.6). Needs 5 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.
bantou
A local MCP server for automating Japanese bookkeeping, including integrations with freee, Yayoi, Money Forward, and TKC. MCP is a standard way for an AI coding tool to call outside tools; this server runs through an npm package and needs three environment variables.
bantou
AI bookkeeping agent for Japanese accountants — auto-classifies freee/Yayoi/MF/TKC transactions. Runs locally from the @kansei-link/bantou npm package.