SMRT Documentation MCP Server

SMRT Documentation MCP Server

Enables querying the SMRT framework documentation by automatically routing questions to relevant package experts and synthesizing responses from their CLAUDE.md files using AI-powered retrieval-augmented generation.

Category
Visit Server

README

@happyvertical/smrt-docs-mcp

Documentation MCP server for the SMRT framework that acts as an orchestrator, routing developer queries to appropriate package experts using CLAUDE.md files.

Overview

The SMRT Documentation MCP Server implements a RAG (Retrieval-Augmented Generation) pattern where each SMRT package's CLAUDE.md file serves as domain expertise. When you ask a question, the server:

  1. Routes your query to relevant packages based on keyword matching
  2. Loads the CLAUDE.md documentation for those packages
  3. Uses AI to synthesize a response based on the expert documentation
  4. Returns an answer with package references

Installation

pnpm install @happyvertical/smrt-mcp

Usage

As an MCP Server

Add to your .mcp.json (see Configuration section below):

{
  "mcpServers": {
    "smrt-advisor": {
      "type": "stdio",
      "command": "pnpm",
      "args": [
        "exec",
        "tsx",
        "/path/to/smrt/packages/smrt-mcp/src/index.ts"
      ],
      "env": {
        "DEBUG": "false"
      },
      "cwd": "/path/to/smrt"
    }
  }
}

Environment Variables

The ask tool requires an AI provider to be configured. Set one of:

  • HAVE_AI_API_KEY - Fallback API key for any provider
  • HAVE_AI_TYPE - Provider type ('openai', 'anthropic', 'gemini')
  • OPENAI_API_KEY - OpenAI API key
  • ANTHROPIC_API_KEY - Anthropic API key
  • GEMINI_API_KEY - Google Gemini API key

Other tools (list-packages, get-docs) work without AI configuration.

Available Tools

ask

Ask a question about the SMRT framework. Automatically routes to relevant packages and synthesizes a response.

Input:

{
  "query": "How do I create a collection with custom actions?",
  "packages": ["core", "products"]  // Optional: specify packages explicitly
}

Example:

Query: "How do I create a collection with custom actions?"

Response:
To create a collection with custom actions in the SMRT framework, you extend SmrtCollection and use the @smrt() decorator to configure which actions are exposed...

---
*Consulted packages: @happyvertical/smrt-core, @happyvertical/smrt-products*

list-packages

List all available SMRT framework packages with descriptions and keywords.

Input:

{
  // No parameters required
}

Example Output:

# SMRT Framework Packages (13 total)

### @happyvertical/smrt-core
Core framework with ORM, code generation, and AI integration

**Keywords**: smrt, framework, orm, database, collection, object...

---

### @happyvertical/smrt-agents
Agent framework for autonomous actors

**Keywords**: agent, autonomous, actor, workflow...

get-docs

Get the full CLAUDE.md documentation for a specific package.

Input:

{
  "packageName": "core"
}

Example:

# @happyvertical/smrt-core

## Purpose and Responsibilities

The `@happyvertical/smrt-core` package is the core framework...

How It Works

Package Registry

The registry scans packages/*/CLAUDE.md files at startup and builds a catalog of available packages with:

  • Package name
  • Description (extracted from CLAUDE.md)
  • Keywords for routing
  • Full documentation content

Query Routing

When you ask a question, the router:

  1. Extracts keywords from your query
  2. Matches against package keyword lists
  3. Scores packages by relevance
  4. Returns top matches

AI Synthesis

The ask tool:

  1. Loads CLAUDE.md for relevant packages (top 3 matches)
  2. Builds context from documentation
  3. Uses AI (via @happyvertical/ai) to generate response
  4. Includes package references in response

Package Keywords

Each package has associated keywords for routing. Examples:

  • core: smrt, framework, orm, database, collection, object, decorator, schema, api, rest, cli, mcp
  • agents: agent, autonomous, actor, workflow, orchestration, task
  • content: content, article, markdown, cms, document, blog, publishing
  • events: event, calendar, meeting, schedule, attendance, rsvp
  • gnode: federation, network, knowledge base, distributed, peer

See src/registry.ts for the complete mapping.

Development

# Build the package
pnpm run build

# Run tests
pnpm test

# Watch mode
pnpm run dev

Configuration

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "smrt-advisor": {
      "command": "pnpm",
      "args": [
        "exec",
        "tsx",
        "/Users/you/path/to/smrt/packages/smrt-mcp/src/index.ts"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "your-key-here"
      }
    }
  }
}

Claude Code

Add to project root .mcp.json:

{
  "mcpServers": {
    "smrt-advisor": {
      "type": "stdio",
      "command": "pnpm",
      "args": [
        "exec",
        "tsx",
        "/Users/you/path/to/smrt/packages/smrt-mcp/src/index.ts"
      ],
      "env": {
        "DEBUG": "false",
        "ANTHROPIC_API_KEY": "your-key-here"
      },
      "cwd": "/Users/you/path/to/smrt"
    }
  }
}

Adding New Packages

When you add a new package to the SMRT framework:

  1. Create a CLAUDE.md file documenting the package
  2. Update src/registry.ts to add keywords for the new package
  3. Rebuild: pnpm run build

The package will be automatically discovered and included in the registry.

Architecture

Developer Query → MCP Server (Orchestrator)
                      ↓
    ┌─────────────────┼─────────────────┐
    ↓                 ↓                 ↓
Package Expert    Package Expert    Package Expert
(@happyvertical/smrt-core)  (@happyvertical/smrt-agents)  (@happyvertical/smrt-content)
CLAUDE.md         CLAUDE.md         CLAUDE.md
    ↓                 ↓                 ↓
    └─────────────────┴─────────────────┘
                      ↓
            Synthesized Response

Troubleshooting

"AI client initialization failed"

The ask tool requires an AI provider. Set one of the environment variables listed above.

"No relevant packages found"

Try using list-packages to see available packages, or specify packages explicitly with the packages parameter.

"Package not found"

Use list-packages to see the exact package names. Package names should not include the @happyvertical/smrt- prefix (use "core" not "smrt-core").

License

MIT

Related

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured