Mikensey MCP Server
Mikensey MCPサーバー
不動産業界向けのMcKinsey流戦略インテリジェンス — Mike DelPreteのContextポッドキャストの53エピソードに基づいています。
Claude(またはMCP互換のAI)が不動産業界のベンチマーク、コンサルティングフレームワーク、全文トランスクリプト検索にアクセスできるようにするオープンソースのMCPサーバーです。2×2マトリックス、SCRメモ、イシューツリー、ポーターのファイブフォースなどを用いて、業界リーダーからの実際のデータに基づいたビジネス状況の分析を依頼できます。
ツール
ツール | 機能 |
| 53件すべてのトランスクリプトの全文検索 |
| ゲストやトピックごとにエピソードを閲覧・フィルタリング |
| トランスクリプトの全文または一部を読み込み |
| 26の業界ベンチマーク(アタッチ率、コスト、成長指標など)をクエリ |
| 10の業界フレームワークと6つのコンサルティングフレームワークを閲覧 |
| コンサルティングフレームワーク(2×2、SCR、イシューツリー、ポーター、バリューチェーン、MECE)を状況に適用 |
| 検索、ベンチマーク、フレームワークを組み合わせたSCR構造の戦略ブリーフ |
Related MCP server: CRE Intelligence MCP
クイックスタート
git clone https://github.com/YOUR_USERNAME/mikensey-mcp-server.git
cd mikensey-mcp-server
npm install
npm run buildClaude Desktopに追加します(Macの場合: ~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"mikensey": {
"command": "node",
"args": ["/path/to/mikensey-mcp-server/dist/index.js"],
"env": {
"MIKENSEY_TRANSCRIPT_DIR": "/path/to/your/transcript-files"
}
}
}
}Claude Desktopを再起動します。ツールメニューに「mikensey」が表示されます。
使用方法
Claudeに自然に話しかけてください:
「2×2マトリックスを使って私の状況を分析して — 私はクラウド型仲介業者にエージェントを引き抜かれている仲介業者です」
「SCR戦略メモを作成して — 私はAIに仕事を奪われることを懸念している住宅ローンLOです」
「Proptechスタートアップが収益性を達成するためのイシューツリーを作成して」
「不動産業界における住宅ローンのベンチマークアタッチ率は?」
「Zillowの戦略を扱っているエピソードはどれ?」
内容
26の業界ベンチマーク — Tamir Poleg (Real)、Glenn Sanford (eXp)、Garth Graham (Stratmore)、Justin Messer (Prosperity) などのリーダーが引用した具体的な数値。アタッチ率、組成コスト、エージェントの生産性、成長指標など。
10の業界フレームワーク — ポッドキャストから得られたメンタルモデル:3レバー消費者価値モデル、仲介プレッツェル、エージェント価値方程式、白兵戦、W-H-Y販売フレームワークなど。
6つのコンサルティングフレームワーク — McKinsey流の分析ツール:2×2マトリックス、状況-複雑性-解決策 (SCR)、イシューツリー (MECE)、ポーターのファイブフォース、バリューチェーン分析、MECE分解。それぞれに不動産の例と構築済みのテンプレートが付属しています。
4つの構築済み2×2マトリックス — 仲介ビジネスモデル、住宅ローン組成戦略、Proptechスタートアップの生存戦略、エージェントの採用と定着 — 企業がプロットされ、トランスクリプトの証拠から洞察が統合されています。
3つの構築済みイシューツリー — 仲介の収益性、住宅ローンの成長戦略、Proptechのプロダクトマーケットフィット — MECEブランチと裏付けデータ付き。
トランスクリプト形式
サーバーは以下のような名前の .txt ファイルを想定しています:
YYYY-MM-DD_guest-name-episode-title.txt例: 2024-03-15_varun-krishna-rockets-next-chapter.txt
設定
環境変数 | デフォルト | 説明 |
|
|
|
開発
npm run dev # Watch mode with tsx
npm run build # Compile TypeScript
npm start # Run compiled server独自のトランスクリプトの使用
このサーバーは、期待される形式のトランスクリプトセットであれば何でも動作します。独自のポッドキャスト、インタビューシリーズ、研究資料に適応させることができます。MIKENSEY_TRANSCRIPT_DIR をファイルがある場所に向けるだけです。
コスト
ゼロ。完全にローカルで実行されます。APIキーも外部サービスも不要で、継続的なコストもかかりません。
ライセンス
MIT
Available Tools
7 toolsmikensey_analyzeMikensey Strategic AnalysisARead-only
Apply a McKinsey-style consulting framework to a business problem using real estate industry data.
This is Mikensey's signature tool. It doesn't just search transcripts — it THINKS like a consultant. Choose a framework, describe your situation, and get a structured strategic analysis backed by real industry evidence.
Available frameworks:
"2x2": 2×2 positioning matrix — plot options across two dimensions to reveal strategic positioning
"scr": Situation-Complication-Resolution — structure a recommendation as an irrefutable argument
"issue_tree": Issue Tree — decompose a complex problem into MECE sub-problems with testable hypotheses
"porters": Porter's Five Forces — analyze competitive dynamics and industry attractiveness
"value_chain": Value Chain Analysis — map where value is created and captured, find integration opportunities
"mece": MECE Breakdown — structure any analysis to be mutually exclusive and collectively exhaustive
Args:
framework (string): Which consulting framework to apply
situation (string): Describe your business context, challenge, or question
role (string): Your role — "agent", "broker", "mortgage_pro", or "founder"
custom_axes (string, optional): For 2×2 only — specify custom axes (e.g., "Growth Rate vs. Profitability")
Returns: A structured strategic analysis using the chosen framework, populated with real industry benchmarks, quotes from leaders, and specific recommendations.
Inputs: framework (required), situation (required), role (required), custom_axes.
mikensey_get_adviceGet Strategic Advice (SCR Format)ARead-only
Get a McKinsey-style strategy brief structured as Situation-Complication-Resolution (SCR), grounded in real industry data from 53 podcast episodes.
This is the executive-ready output tool. It generates a complete strategy memo using the SCR framework:
SITUATION: Undeniable facts about the current state (backed by benchmarks)
COMPLICATION: What has changed or is broken (backed by transcript evidence)
RESOLUTION: Specific recommendations with supporting data
For deeper analysis with specific frameworks (2×2, Issue Trees, Porter's, etc.), use mikensey_analyze instead.
Args:
role (string): Your role — "agent", "broker", "mortgage_pro", or "founder"
situation (string): Describe your business situation and challenge in detail
topic (string, optional): Focus area — "growth", "retention", "mortgage", "tech", "differentiation", "profitability"
Returns: An SCR-structured strategy brief with benchmarks, evidence, and specific recommendations.
Inputs: role (required), situation (required), topic.
mikensey_get_benchmarksGet Industry BenchmarksARead-onlyIdempotent
Look up real estate, mortgage, and proptech industry benchmarks and metrics from podcast conversations.
Contains specific numbers cited by industry leaders: attach rates, origination costs, agent productivity, growth rates, conversion rates, and more.
Args:
query (string, optional): Filter benchmarks by keyword (e.g., "mortgage", "agent", "cost")
Returns: Benchmark data with metric name, value, context, and source.
Examples:
"attach rate" → mortgage attach rate benchmarks from Prosperity, industry averages
"cost" → origination costs, marketing costs, compliance costs
"agent" → agent counts, growth rates, retention metrics
No query → returns all benchmarks
Inputs: query.
mikensey_get_episodeGet Mikensey Episode TranscriptARead-onlyIdempotent
Read the full or partial transcript of a specific podcast episode.
Use this to deep-dive into a specific conversation. Use mikensey_list_episodes or mikensey_search first to find the episode id.
Args:
episode_id (string): Episode slug (e.g., "justin-messer-hand-to-hand-combat-in-mortgage")
offset (number): Start reading from this line number (default: 0)
limit (number): Number of lines to return (default: 200)
Returns: Episode transcript text with metadata.
Inputs: episode_id (required), offset, limit.
mikensey_get_frameworksGet Strategy FrameworksARead-onlyIdempotent
Browse two categories of frameworks available in Mikensey:
Industry Frameworks — Mental models extracted from podcast conversations (e.g., 3-Lever Consumer Value Model, Brokerage Pretzel, Agent Value Equation, W-H-Y mortgage sales)
Consulting Frameworks — McKinsey-style analytical tools you can apply to any problem (2×2 Matrix, SCR, Issue Trees, Porter's Five Forces, Value Chain, MECE)
Args:
audience (string, optional): Filter industry frameworks by target audience — "agents", "mortgage", or "founders"
type (string, optional): Filter by framework type — "industry" (from podcasts) or "consulting" (McKinsey toolkit) or "all" (default)
Returns: Framework name, description, when to use, and examples.
To actually APPLY a consulting framework to your specific situation, use mikensey_analyze.
Inputs: audience, type.
mikensey_list_episodesList Mikensey EpisodesARead-onlyIdempotent
List all available podcast episodes with guest names, dates, and topics.
Use this to browse what's available or find a specific episode.
Args:
filter (string, optional): Filter by guest name, topic, or keyword
limit (number): Max results (default: 20)
offset (number): Skip this many results for pagination (default: 0)
Returns: Episode list with id, guest, title, date, and word count.
Inputs: filter, limit, offset.
mikensey_searchSearch Mikensey Knowledge BaseARead-onlyIdempotent
Search across all Mike DelPrete podcast transcripts for topics, quotes, metrics, or advice.
Use this tool to find what industry leaders have said about specific topics in real estate, mortgage, and proptech.
Args:
query (string): Search terms (e.g., "mortgage attach rate", "agent retention", "AI in real estate")
limit (number): Max results to return (default: 5, max: 10)
Returns: Matching transcript excerpts with episode info, guest name, and relevant quotes.
Examples:
"mortgage attach rate" → finds discussions about mortgage integration success rates
"agent equity ownership" → finds eXp and Real Brokerage discussions
"cost of origination" → finds Stratmore Group data on mortgage economics
Inputs: query (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose with no overlap: mikensey_analyze applies frameworks, mikensey_get_advice generates SCR briefs, mikensey_get_benchmarks retrieves metrics, mikensey_get_episode fetches transcripts, mikensey_get_frameworks lists frameworks, mikensey_list_episodes shows episodes, and mikensey_search queries transcripts. The descriptions explicitly differentiate them, such as advising to use mikensey_analyze for specific frameworks versus mikensey_get_advice for SCR memos.
All tools follow a consistent snake_case naming pattern with the prefix 'mikensey_' and clear verb_noun combinations: analyze, get_advice, get_benchmarks, get_episode, get_frameworks, list_episodes, and search. This uniformity makes the tool set predictable and easy to navigate, with no deviations in style or convention.
With 7 tools, the server is well-scoped for its purpose of providing McKinsey-style consulting analysis on real estate industry data. Each tool serves a specific function—from analysis and advice to data retrieval and search—without redundancy, making the count ideal for covering the domain comprehensively without being overwhelming.
The tool set offers complete coverage for the domain, including analysis (mikensey_analyze), advice generation (mikensey_get_advice), data access (mikensey_get_benchmarks, mikensey_get_episode, mikensey_list_episodes), framework browsing (mikensey_get_frameworks), and search (mikensey_search). There are no obvious gaps; agents can perform end-to-end tasks from exploration to structured recommendations without dead ends.
Related MCP Connectors
AI-native real estate discovery with structured property search and market intelligence.
AI agent access to your Searcher OS deal feed, pipeline, buy boxes, CIM analysis, and broker CRM.
Research, strategy, financial models and decks, priced and approved per job, in your AI assistant
Podcast knowledge for AI agents: search episodes, pull transcripts and ask questions.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI assistants to answer mortgage-related queries by providing tools for lender search, loan limit lookup, down-payment assistance programs, and more, with data sourced from real wholesale lenders and broker-curated intel.810 npmMIT
- AlicenseNot gradedqualityDmaintenanceProvides live commercial real estate data (rates, demographics) and analysis tools (DCF, rent roll parsing, lease abstraction, IC memo generation) within Claude Desktop.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to perform real-time business intelligence tasks including competitive analysis, website scoring, review analysis, and market research.MIT
- AlicenseNot gradedqualityDmaintenanceProvides comprehensive real estate market intelligence, property valuation, and investment analysis for AI agents. Unifies data from multiple sources like Zillow, Redfin, and public records into a single MCP interface.MIT