The Build Vault MCP Server

<div align="left"> <img src="screenshots/build-logo-transparent.svg" alt="BUILD" width="250" /> </div>

Overview

A Model Context Protocol (MCP) server that transforms The Build Podcast into a searchable knowledge base with thousands of AI insights using advanced hybrid search. Combines vector semantic similarity with full-text search to help you discover business ideas, frameworks, and product strategies. Access the collective wisdom of builders and entrepreneurs through natural language queries, making podcast knowledge instantly actionable.

Background

Our MCP Server sources it's information from The Build Vault. The Build Vault is an intelligent archive of AI-focused insights, products, ideas and news extracted from The Build Podcast episodes. The backend powers a sophisticated AI-driven data processing pipeline that consists of the following stages:

Core Processing Pipeline

• YouTube Episode Extraction and Audio Download
• AssemblyAI Transcriptions with speaker diarization, sentiment analysis, and auto highlights
• Segment Processing with AI-enhanced titles, topics, and key phrases

LLM Driven Content Extraction

• 150-250 word summaries
• Extract insights across Frameworks & Exercises, Points of View, Business Ideas, Stories & Anecdotes, Quotes, and Products
• Product Extraction: Automatically identifies and tracks product mentions from insights, preparing them for enrichment workflows
• Link Processing: Extracts URLs from YouTube descriptions and enriches them with AI-powered summaries, categorization, and key takeaways

Advanced Search & Discovery

• Vector Embeddings: Generates embeddings for semantic search capabilities
• Hybrid Search: Combines vector similarity search with full-text search

MCP Client Configuration

Known Client Compatibility:

• Claude Desktop
• Claude Code
• Goose
• OpenAI ChatGPT (chat.openai.com)
• OpenAI Playground

Claude Desktop

{
  "mcpServers": {
    "build-vault": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.buildaipod.com/mcp"]
    }
  }
}

Claude Code

claude mcp add build-vault -s user --transport http https://mcp.buildaipod.com/mcp

<img src="screenshots/claude-desktop-tools.png" alt="Claude Desktop Tools" width="250" /> <img src="screenshots/claude-desktop-resources-prompts.png" alt="Claude Desktop Resources and Prompts" width="250" />

Goose AI Extension

<img src="screenshots/goose-config.png" alt="Goose Configuration" width="250" />

OpenAI ChatGPT (Custom Connectors)

<img src="screenshots/openai-chatgpt-connector.png" alt="OpenAI ChatGPT Connector" width="250" />

OpenAI Playground

<img src="screenshots/openai-playground-config.png" alt="OpenAI Playground Configuration" width="250" />

MCP Version Compatability

MCP 2025-06-18 Compliance

• Protocol Version: 2025-06-18 with full specification compliance
• Structured Output: Enhanced tools with outputSchema and structuredContent
• Elicitation Support: Declared capability with intelligent follow-up suggestions
• Title Fields: All tools, resources, and prompts include descriptive titles
• Resource Links: Cross-referencing between related content
• Transports: stdio + Streamable HTTP

Enhanced Compatability

• OpenAI Deep Research: Compatible with OpenAI's Deep Research Custom Connectors

Vault Discovery Tools (12 Total)

• List Products: Browse AI products with filtering and pagination
• Search Products: Semantic search using embeddings (3072 dimensions)
• Product Details: Comprehensive product information with resource links
• Find Similar: Vector similarity search for related products
• Search by Speaker: Filter insights by podcast speakers (Tom Spencer, Cameron Rohn)
• Search by Date Range: Find products within specific time periods
• Search by Category: Filter by 6 content categories (business_ideas, frameworks_and_exercises, products, points_of_view, stories_and_anecdotes, quotes)
• Search by Timeframe: Find insights within episode timestamps
• Speaker Summary: Comprehensive speaker statistics and insights
• Timeline Insights: Chronologically ordered insights with metadata
• Search (Deep Research): Natural language search for AI insights and episodes
• Fetch (Deep Research): Get complete content with full context and metadata

Analytics Resources with Elicitation (4 Total)

• Trending Insights: High-confidence insights with smart follow-up suggestions
• Category Distribution: Live analytics on content breakdown by category
• Episode Timeline: Chronological episode data with insight counts
• Speaker Analytics: Real-time speaker statistics and content analysis

Guided Prompts (4 Total)

• Find Business Ideas: Discover business insights and opportunities
• Explore Frameworks: Structured exploration of frameworks and exercises
• Timeline Analysis: Chronological exploration of topics and themes
• Compare Content Types: Compare different categories of insights

Enhanced Elicitation Features

When accessing resources, the server provides intelligent follow-up suggestions:

• Category Analysis: "Found 9 product insights, 6 points_of_view insights"
• Speaker Breakdown: "Cameron Rohn (11 insights), Tom Spencer (8 insights)"
• Tool Recommendations: Specific next-step suggestions with usage examples
• Semantic Search Guidance: Query suggestions based on actual content

OpenAI Deep Research Integration

This server is compatible with OpenAI's Deep Research Custom Connectors. The search and fetch tools are specifically designed to work with Deep Research models:

• Search Tool: Accepts natural language queries (e.g., "insights about AI agents") and returns results in the format {id, title, text, url}
• Fetch Tool: Retrieves complete content with metadata for deep analysis and citation

Usage Examples

Discovering AI Products

1. Browse Categories: Use search_by_category with "products" to see 334 product insights
2. Semantic Search: Try search_products with "AI agents" or "LangChain"
3. Trending Content: Access vault://trending_insights resource for top 20 high-confidence insights
4. Follow Suggestions: Look for "What's Next?" sections with intelligent recommendations

Example Searches

Try these searches to get started:

• "What frameworks exist for prompt engineering?"
• "Business ideas in the healthcare AI space"
• "What did Tom Spencer say about LangChain?"
• "Insights about AI safety and alignment"
• "Products for building chatbots"

Available Tools

Available Resources

Available Prompts

---