my-mcp-server

An MCP server that exposes Aniket Charjan's resume as a queryable API for AI assistants. Add it to Claude Desktop, Cursor, or any MCP client and ask "What did Aniket do at BrowserStack?" or "Has he shipped anything with WebRTC?" — answered from structured, sourced data instead of guesswork.

Real output from the server — has_skill returns evidence rather than a yes/no, and search_background cites the project or skill group each match came from.

It implements all three MCP primitives — Tools, Resources, and Prompts — so it works as a complete reference server, not just a tool dump.

Tools

Related MCP server: personal-resume-agent

Resources

Prompts

Use it

No install and no npm account needed — npm can run it straight from this repo:

npx -y github:jason-bourne-gg/my-mcp-server

That clones the repo, builds it, and starts the server on stdio.

Or clone it yourself if you want to poke at the source:

git clone https://github.com/jason-bourne-gg/my-mcp-server.git
cd my-mcp-server
npm install && npm run build

Claude Desktop

Add to claude_desktop_config.json (Settings → Developer → Edit Config), using the absolute path to the built file:

{
  "mcpServers": {
    "aniket": {
      "command": "node",
      "args": ["/absolute/path/to/my-mcp-server/dist/index.js"]
    }
  }
}

Restart Claude Desktop, then ask: "Using the aniket tools, what's his experience with LLMs?"

Cursor

Add the same block to ~/.cursor/mcp.json (or Settings → MCP).

To skip the build step entirely, point the client at the repo instead:

{
  "mcpServers": {
    "aniket": {
      "command": "npx",
      "args": ["-y", "github:jason-bourne-gg/my-mcp-server"]
    }
  }
}

Develop

npm install
npm run build     # tsc → dist/
npm start         # run the built server on stdio

Smoke-test over stdio without a client:

printf '%s\n' \
  '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"t","version":"1"}}}' \
  '{"jsonrpc":"2.0","method":"notifications/initialized"}' \
  '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' \
  '{"jsonrpc":"2.0","id":3,"method":"resources/list","params":{}}' \
  '{"jsonrpc":"2.0","id":4,"method":"prompts/list","params":{}}' \
  | node dist/index.js

All content lives in src/data.ts — edit there and rebuild.

How it works

A stdio MCP server built on @modelcontextprotocol/sdk. It registers the tools, resources, and prompts capabilities and handles the corresponding list / call / read / get requests. search_background and has_skill run over a flattened index of every experience highlight, project, and skill, returning each hit with its source. Tool handling is wrapped so a single bad request can never crash the server, and SIGINT/SIGTERM shut it down cleanly.

License

MIT © Aniket Ravindra Charjan