Interop · Module 07 · Intermediate

MCP: the USB-C of AI

Model Context Protocol (MCP) is the plug standard for AI. Anthropic proposed it in late 2024; by 2026 every major AI app supports it. If you learn one interoperability layer, learn this one.

What MCP actually is

MCP is an open protocol for connecting AI applications ("clients") to data sources and tools ("servers"). Think of it like USB-C: any compliant server plugs into any compliant client.

Perplexity Computer MCP client Claude Desktop MCP client Cursor MCP client MCP JSON-RPC over stdio / HTTP Figma server GitHub server Filesystem server Your custom server
Many clients. Many servers. One protocol. Install once, use everywhere.

What an MCP server exposes

  • Tools — actions the client can call (like function calling, but standardized).
  • Resources — data the client can read (files, database rows, docs).
  • Prompts — reusable prompt templates that any client can list and invoke.
ServerWhat it doesFor you
FilesystemRead/write local filesLet Claude Desktop safely edit files in a chosen folder
GitHubRepos, issues, PRs, commitsAlready available in Computer as a connector; also as MCP
Figma Dev Mode MCPRead Figma frames, components, tokensDirectly relevant — pipe your Figma into any AI IDE
CloudflareWorkers, KV, R2, VectorizeDeploy from Claude Desktop / Computer
PlaywrightReal browser automationAutomate RFP portal scraping
Notion / Slack / LinearStandard SaaS integrationsYour PM stack, one install

Install your first MCP server (2 minutes)

In Claude Desktop, edit ~/Library/Application Support/Claude/claude_desktop_config.json:

JSON{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/Users/you/business-docs"
      ]
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_yourtoken" }
    }
  }
}

Restart Claude Desktop. You now have file-system and GitHub tools inside every conversation.

Writing your own MCP server (skeleton)

Python · MCP SDKfrom mcp.server.fastmcp import FastMCP

mcp = FastMCP("my-business-tools")

@mcp.tool()
def estimate_project(scope: str, pages: int) -> dict:
    """Estimate cost + timeline for a web project.

    Args:
        scope: high-level description of the work
        pages: number of unique page templates

    Returns: dict with low_usd, high_usd, weeks
    """
    base = 4000 + pages * 1200
    return {
        "low_usd": base,
        "high_usd": int(base * 1.6),
        "weeks": max(3, pages // 2),
    }

if __name__ == "__main__":
    mcp.run()

Add it to claude_desktop_config.json and Claude can now call estimate_project in any conversation. Same server plugs into Cursor, Windsurf, or any MCP-aware client with zero changes.

Why this matters for a small business

Your custom internal tools — cost estimator, quote generator, requirement extractor, inventory checker — become portable. Build once, use in every AI app you touch. No vendor lock-in.

Exercise · 15 min

Install and use one MCP server today

  1. Install Claude Desktop if you don't have it.
  2. Add the filesystem server pointing at a scratch folder.
  3. Ask Claude: "Look at every .pdf in that folder and tell me which look like RFPs."
  4. Watch it use the list_directory and read_file tools live.
Or pass the quiz above.