AI & MCP Support

@express-route-cache provides structured AI manifests so your coding assistant gives accurate, hallucination-free answers about the library.

Quick Comparison

Method	Setup	Best for...
Perplexity	❌ None	Quick one-off questions
Cursor @Docs	✅ Paste URL	Continuous indexing while coding
Native MCP	✅ Config file	Deep research in Claude/Windsurf/VS Code

---

✦ Perplexity (Zero Setup)

Perplexity browses our documentation in real-time. No installation needed.

Ask Perplexity →

---

🛠️ Cursor — @Docs

1. Cmd + Shift + J → Cursor Settings → General → Documentation
2. Click + Add new doc
3. Paste: https://express-route-cache.js.org/llms-full.txt
4. Name it @express-route-cache

Now type @express-route-cache in Cursor Chat to get library-aware answers.

---

🤖 Native MCP (Claude, VS Code, Windsurf, Cursor)

We provide a dedicated MCP server that gives your AI live access to our documentation, API reference, and common patterns.

Configuration

Add the following JSON block to the config file for your tool. No extra installation is needed if you have Node.js.

{
  "mcpServers": {
    "express-route-cache": {
      "command": "npx",
      "args": [
        "-y",
        "@express-route-cache/mcp"
      ]
    }
  }
}

Config file locations:

Tool	File path
Claude Desktop (macOS)	~/Library/Application Support/Claude/claude_desktop_config.json
Claude Desktop (Windows)	%APPDATA%\Claude\claude_desktop_config.json
Cursor (global)	~/.cursor/mcp.json
VS Code + Copilot	.vscode/mcp.json — use "servers" instead of "mcpServers"
Windsurf (macOS)	~/.codeium/windsurf/mcp_config.json

Capabilities

Once connected, your AI assistant gains these "Tools":

• get-docs: Fetches the entire library documentation for context.
• get-page: Fetches specific deep-dive pages (e.g., guide/concepts-swr).

---

📄 Technical Manifests

Consume these directly in your own AI pipelines:

File	URL	Purpose
llms.txt	/llms.txt	Quick context primer
llms-full.txt	/llms-full.txt	Full API docs + examples
ai.json	/ai.json	Machine-readable manifest