AI Integration

The Model Context Protocol (MCP) lets AI assistants like Claude, GPT, and Gemini connect directly to external data sources. By connecting your session data via MCP, you can have a conversation with your data — ask questions, explore responses, and get AI-generated analysis of what participants said.

What Can You Do?

Once connected, try asking your AI assistant questions like:

•"What sessions do I have?"
•"Show me the responses from my last session"
•"Summarize the key themes across all responses"
•"Search for responses mentioning machine learning"

We'll email you a secret link for your MCP server. Do not share this link — it provides full access to your session data.

Setup Instructions

After you receive your MCP server URL via email, follow the instructions below for your platform. Your URL will look like: https://api.futureofcomputing.org/api/mcp/abc12DEf_g-h

Claude.ai (web)

Go to Settings → Connectors, click Add custom connector, enter a name (e.g. "Future of Computing"), paste your MCP URL, and click Add. Then in any conversation, click the + button and select Connectors to enable it. Full instructions →

ChatGPT (web)

On chatgpt.com, go to Settings → Apps → Advanced settings and enable Developer mode. Then click Create app, enter a name, paste your MCP URL, check "I trust this application", and click Create. Requires a paid ChatGPT plan. Full instructions →

Claude Desktop

Open your Claude Desktop configuration file (claude_desktop_config.json) and add:

{
  "mcpServers": {
    "futureofcomputing": {
      "type": "streamablehttp",
      "url": "YOUR_MCP_URL"
    }
  }
}

Claude Code

Add to your project's .mcp.json file, or run claude mcp add futureofcomputing YOUR_MCP_URL. Full instructions →

{
  "mcpServers": {
    "futureofcomputing": {
      "type": "streamablehttp",
      "url": "YOUR_MCP_URL"
    }
  }
}

Gemini

The consumer Gemini web app does not currently support custom MCP servers. MCP is available through Gemini Enterprise (Google Cloud) and the Gemini CLI.