Create xmcp Resource

Step 1: Gather Information

1. Resource name (if not provided): What should the resource be named? (Use kebab-case)
2. Resource type: Ask which type of resource they need:
   • Static - Fixed content that doesn't change (configuration, documentation)
   • Dynamic - Content that depends on parameters (user profiles, reports)
   • File-based - Content read from files (logs, data files)
3. URI pattern: How should the resource be accessed?
   • Simple:

     config://app

     or

     docs://readme

   • With parameters:

     users://[userId]/profile

   • Nested:

     reports://[year]/[month]/summary

4. Content details:
   • What is the content about?
5. Widget support (optional): Ask if they need OpenAI widget rendering.

Step 2: Generate the Resource

src/resources/

File Location & Routing

src/resources/
├── (config)/              # Route group (not in URI)
│   └── app.ts            # → config://app
├── (users)/
│   └── [userId]/         # Dynamic segment
│       └── profile.ts    # → users://[userId]/profile
└── docs/
    └── readme.ts         # → docs://readme

• (folder)

  - Route group, excluded from URI path

• [param]

  - Dynamic parameter segment
• Filename becomes the final URI segment

Resource Structure Reference

// 1. Metadata (optional) - Resource configuration
export const metadata: ResourceMetadata = { /* ... */ };

// 2. Handler (required) - Default export function
export default function handler(params?) { /* ... */ }

// 3. Schema (optional) - For dynamic resources with parameters
export const schema = { /* ... */ };

Quick Reference

Essential Imports

import { type ResourceMetadata } from "xmcp";

// For dynamic resources
import { z } from "zod";
import { type InferSchema, type ResourceMetadata } from "xmcp";

Metadata Fields

name

title

description

mimeType

size

_meta

Handler Return Types

string

{ text: string }

{ blob: Uint8Array, mimeType: string }

JSON.stringify(data)

Detailed Templates

• Static resource patterns
• Dynamic resource with parameters
• File-based resources
• Nested routing examples
• OpenAI metadata examples

references/patterns.md

Checklist After Generation

1. File created in correct

   src/resources/

   location
2. If using metadata, ensure it has descriptive

   name

   and

   description

3. Schema uses

   .describe()

   for all parameters (if dynamic)
4. Handler returns appropriate content type
5. File path matches intended URI pattern

pnpm build