No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by freee · MCP Server · ★ 500
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is freee-mcp safe to install? View the security audit →
freee-mcp freee API を Claude から使えるようにする MCP サーバー & Claude Plugin です。 MCP サーバー(API 呼び出し機能)と skill(API リファレンス)を組み合わせて利用することを想定しています。 Note: このプロジェクトは開発中であり、予期せぬ不具合が発生する可能性があります。問題を発見された場合は Issue として報告していただけると幸いです。 特徴 MCP サーバー: freee API を Claude Desktop / Claude Code から直接呼び出し Claude Plugin: 詳細な API リファレンスドキュメント付きスキルを提供 複数 API 対応: 会計・人事労務・請求書・工数管理・販売の5つの freee API をサポート OAuth 2.0 + PKCE: セキュアな認証フロー、トークン自動更新 複数事業所対応: 事業所の動的切り替えが可能 SKILL と MCP の通信の流れ Claude Code では、SKILL(API リファレンス)と MCP サーバー(API 呼び出し)を組み合わせて利用します。 この仕組みにより: SKILL: 必要な API リファレンスを段階的にコンテキスト
| Stars | 500 |
| Forks | 57 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 66.8583044335418/100 |
| Open Issues | 8 |
| Last Updated | 2026-09-16 |
| Created | 2025-01-29 |
| Platforms | mcp, node |
| Est. Tokens | ~16k |
These tools work well together with freee-mcp for enhanced workflows:
Explore other popular mcp server tools:
freee-mcp is Model Context Protocol (MCP) server for freee API integration. It is categorized as a MCP Server with 500 GitHub stars.
freee-mcp is primarily written in TypeScript.
You can find installation instructions and usage details in the freee-mcp GitHub repository at github.com/freee/freee-mcp. The project has 500 stars and 57 forks, indicating an active community.
freee-mcp is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: