MCP

Point your AI tools at my work.

This site runs a Model Context Protocol server. Connect it once and Claude Code, Cursor or any MCP client can answer questions about my background from the source, rather than you reading pages or me sending a PDF.

Claude Code

One command:

claude mcp add --transport http syedali https://syedali.me/api/mcp

Add --scope user to make it available in every project.

Cursor, and anything else

Add it to your MCP config file - .cursor/mcp.json for Cursor,.mcp.json for Claude Code, or wherever your client keeps them:

{
  "mcpServers": {
    "syedali": {
      "type": "http",
      "url": "https://syedali.me/api/mcp"
    }
  }
}

Then ask

  • “What has Syed shipped in financial crime?”
  • “Summarise his experience with design systems.”
  • “Does he have core banking experience? Where?”
  • “Is he a fit for a senior product design role in fintech?”

What it exposes

search_portfolio
Search everything - roles, case studies, skills, outcomes. The one to reach for first.
get_profile
Who I am, where I am, what I am working on now.
get_work_history
Every role in reverse chronological order, with what I did there.
get_case_studies
The case studies, with summaries and links.
get_skills
Skills grouped into design, research, engineering and domains.
get_highlights
Shipped outcomes with numbers attached.

The endpoint

https://syedali.me/api/mcp

Streamable HTTP transport, stateless, no authentication and no API key. POST JSON-RPC to it; a GET returns 405 because the server never initiates messages.

What it will not tell you

Everything the server returns is already public on this site. The one confidential case study is listed by title and summary only - the write-up, the process work and the imagery stay behind the password. Ask me on LinkedIn if you need access.

© 2026 Syed Ali