**XIRR（拡張内部収益率）**を計算するためのMCPサーバーです。楽天証券の取引履歴CSVの読み込みを標準サポートしています。
Claude DesktopやClaude Codeに組み込み、証券会社からエクスポートしたCSVを渡して以下のように質問してください：
「この CSV と現在の評価額 ¥1,500,000 で、実績年利を計算して」
Claudeが不定期な入出金を考慮してXIRRを計算し、結果を解説します。
🧮 calculate_xirr — 任意のキャッシュフローと現在の評価額からXIRRを計算
📄 parse_rakuten_csv — 楽天証券の取引履歴CSVを正規化されたキャッシュフローに変換
🔌 ネットワークアクセス不要の純粋なstdio MCPサーバー
📦 ランタイム設定不要、npxコマンド一つで実行可能
Related MCP server: ibkr-mcp
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) または %APPDATA%\Claude\claude_desktop_config.json (Windows) を編集します：
{
"mcpServers": {
"xirr": {
"command": "npx",
"args": ["-y", "@kimagure-dd/xirr-mcp"]
}
}
}Claude Desktopを再起動してください。calculate_xirr および parse_rakuten_csv ツールが表示されるはずです。
claude mcp add xirr -- npx -y @kimagure-dd/xirr-mcpClaudeに以下のように尋ねます：
「以下のキャッシュフローで XIRR を計算して。2020-01-01 に 100万円投資、2022-01-01 に 50万円追加、現在（2025-01-01）の評価額 200万円」
Claudeは構造化された入力で calculate_xirr を呼び出し、以下を返します：
{
"annualRate": 12.34,
"annualRateFormatted": "12.34%",
"totalInvestment": 1500000,
"totalGain": 500000,
"gainRateFormatted": "33.33%",
"converged": true
}楽天証券にログイン → 取引履歴 → CSV ダウンロード
(Shift_JIS でダウンロードされるため UTF-8 に変換してください)
Claude にファイル内容を渡して「これで実績年利を計算して。現在の評価額は ¥X」と依頼
Claudeは自動的にCSVを parse_rakuten_csv → calculate_xirr の順で処理します。
calculate_xirr日付付きキャッシュフローのリストと現在の評価額からXIRRを計算します。
入力:
フィールド | 型 | 説明 |
| array |
|
| number | 現在のポートフォリオ評価額。 |
| string | YYYY-MM-DD。 |
出力:
フィールド | 型 | 説明 |
| number | 年率換算された収益率（パーセント）。 |
| number | 月率（年率に複利換算）。 |
| number | 全キャッシュフローの合計。 |
| number |
|
| number | 投資額に対する合計利益率（パーセント）。 |
| boolean | 反復計算が収束した場合は true。 |
parse_rakuten_csv楽天証券の取引履歴CSVを解析します。
入力:
フィールド | 型 | 説明 |
| string | 生のCSVテキスト（UTF-8デコード済み）。 |
必要なCSVヘッダー:
約定日, 取引, ファンド名, 受渡金額/(ポイント利用)[円]
動作:
買付 行 → 正の金額（投資）
その他の取引タイプ（例: 売却） → 負の金額（引き出し）
無効な行は警告とともにスキップされます
メインソルバーとしてニュートン・ラフソン法を使用
ニュートン法で収束しない場合は二分法にフォールバック
時間単位: 月（1ヶ月あたり 365.25 / 12 日を使用）
収束閾値: 1e-7
kimagure-dd.devのブラウザ版XIRR計算機 と同じロジックを使用しているため、結果は同一です。
本ツールは情報提供のみを目的として投資パフォーマンスを計算します。 税金、取引手数料、為替換算は考慮されていません。 出力は投資助言を構成するものではありません。
npm install
npm run build
npm test公開前にローカルでサーバーをテストするには：
npm pack
# Then point Claude Desktop to the .tgz pathMIT © kimagure-dd
🌐 kimagure-dd.dev — ブラウザベースの金融計算ツール
🐙 ソースコード
Calculate XIRR (Extended Internal Rate of Return) from a series of dated cash flows and a current portfolio valuation. Returns annualized rate, monthly rate, total gain, and convergence status. Useful for measuring actual investment performance accounting for irregular contributions and withdrawals.
| Name | Required | Description | Default |
|---|---|---|---|
| cashFlows | Yes | List of cash flows. Use positive amounts for investments (buy), negative for withdrawals (sell). | |
| currentValue | Yes | Current valuation of the portfolio at valuationDate. | |
| valuationDate | Yes | Date of the current valuation in YYYY-MM-DD format. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It indicates the outputs (annualized rate, monthly rate, total gain, convergence status) but does not mention potential issues like convergence failures, input validation, or performance limitations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, front-loaded with the purpose and return values. Every word is informative and there is no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, the description adequately lists the return values (annualized rate, monthly rate, total gain, convergence status). It covers the essential outputs for a financial calculation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage, so the description adds limited semantic value beyond what's already documented. It reiterates that positive amounts are investments, which is already in the schema, but does not provide new details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Calculate XIRR' and the resource 'from a series of dated cash flows and a current portfolio valuation'. It distinguishes this tool from its sibling parse_rakuten_csv, which handles CSV parsing, by focusing on financial computation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool ('useful for measuring actual investment performance...'), but does not explicitly mention when not to use it or provide alternatives. However, given the distinct sibling tool, no confusion arises.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Parse a Rakuten Securities transaction CSV (取引履歴) and convert it into a normalized cash flow list. Handles 買付/売却 transaction types automatically. The output can be fed directly into calculate_xirr.
| Name | Required | Description | Default |
|---|---|---|---|
| csvContent | Yes | Raw CSV text exported from Rakuten Securities. Note: Rakuten exports are typically Shift_JIS encoded; decode to UTF-8 before passing. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the automatic handling of transaction types and encoding issues, but lacks details on error behavior, file size limits, or other edge cases. It is partially transparent but leaves gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences that are efficiently front-loaded. The first sentence states the core purpose, the second adds key details. Every sentence is meaningful with no superfluous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple tool (1 param, no output schema), the description covers input format, handling, and integration with calculate_xirr. It could mention the output structure more explicitly, but it is sufficient for an agent to understand usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 100% coverage with a single parameter. The description adds value by explaining the parameter is raw CSV text and specifically notes the Shift_JIS encoding issue, which is critical for correct usage. This exceeds the baseline of 3 for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool parses Rakuten Securities transaction CSV and converts to normalized cash flow list, handling specific transaction types. It implicitly distinguishes from the sibling tool calculate_xirr by indicating the output feeds into it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says when to use the tool (when you have a Rakuten Securities CSV) and hints at the workflow with calculate_xirr. It provides encoding context but doesn't explicitly state when not to use it or list alternatives, though the sibling count is low.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0calculate_xirrparse_rakuten_csvScored across 2 tools
The two tools have clearly distinct purposes: parse_rakuten_csv converts a specific CSV into cash flows, and calculate_xirr performs the actual rate calculation. No overlap exists.
Both tools follow a consistent verb_noun pattern using snake_case: parse_rakuten_csv and calculate_xirr. Perfectly consistent.
With only 2 tools, the server is very focused but appropriately scoped for the specific use case of Rakuten CSV processing and XIRR calculation. A slightly broader tool count could be argued, but it's reasonable.
For the domain of computing XIRR from Rakuten CSV data, the server is complete. The parse-then-calculate workflow covers all necessary steps without missing functionality.
MCP server for VC pitch-deck scoring, thesis-fit matching, and deal-flow management.
Research-only MCP server: your AI as a quant research desk. 90 tools, no trades, no brokers.
Research US-listed companies and funds with the StockPortfolio.pro MCP server. Tools cover SEC filing-grounded financials, filing timelines, company comparisons, watchlist screens, fund profiles, and cited filing questions. Filed figures include their fiscal period and EDGAR source URL; missing filing data is returned as null. Public tools work without authentication; optional API-key or OAuth access is supported. US-listed, USD-reporting companies only. Keyless access includes 3 free AI questions per rolling 30-day window. To get more now, choose the Dev plan ($19.99/month, 200 credits) at https://www.stockportfolio.pro/register?plan=dev, then follow https://www.stockportfolio.pro/docs/api-mcp to connect with OAuth or an API key. Or wait for the free allowance to renew.
MCP server exposing the Backtest360 engine API as tools for AI agents.
