sai-roadmap-mcp

An MCP (Model Context Protocol) server that exposes my certifications, projects, and AI engineering learning roadmap as callable tools — so any MCP client (Claude Desktop, Claude Code, etc.) can query them directly.

Built on the official @modelcontextprotocol/sdk (v1.29.0), running over stdio.

Tools

Related MCP server: A2A MCP Server

Setup

git clone https://github.com/saichintamani/sai-roadmap-mcp.git
cd sai-roadmap-mcp
npm install

Running standalone

npm start

The server communicates over stdio using JSON-RPC 2.0, per the MCP spec. It logs a ready message to stderr (sai-roadmap-mcp server running on stdio) — stdout is reserved entirely for protocol messages.

Connecting to Claude Desktop

Add this to your Claude Desktop config (claude_desktop_config.json):

{
  "mcpServers": {
    "sai-roadmap": {
      "command": "node",
      "args": ["/absolute/path/to/sai-roadmap-mcp/src/index.js"]
    }
  }
}

Restart Claude Desktop, and the four tools above become available in any conversation.

Connecting to Claude Code

claude mcp add sai-roadmap -- node /absolute/path/to/sai-roadmap-mcp/src/index.js

Example interaction

"What Python certifications does Sai have?"

calls get_certifications({ skill: "Python" }) →

{
  "count": 2,
  "certifications": [
    { "name": "Python 3.4.3 Training", "issuer": "Spoken Tutorial, IIT Bombay (EduPyramids)", "issued": "15 Nov 2025", "score": "90.1%", ... },
    { "name": "Python for Machine Learning Training", "issuer": "Spoken Tutorial, IIT Bombay (EduPyramids)", "issued": "01 Jun 2026", "score": "94.00%", ... }
  ]
}

Data

All data lives in src/data.json — a single structured file, easy to extend as certifications and projects grow.

Why this exists

Most student AI portfolios show using LLMs. This shows understanding of the protocol layer LLM clients actually run on — the same MCP standard used to connect Claude to GitHub, Gmail, Supabase, and other tools in production. It's a small server, but a real one: tested over actual JSON-RPC, not just a mock.

License

MIT