MCP Support (BETA)

⚠️ BETA FEATURE - This feature is currently in BETA and subject to change. Review all generated content before use.

What is MCP?

MCP (Model Context Protocol) is a standardized protocol that allows AI agents to interact with Playground in a structured, safe way. Instead of manually creating plays step-by-step, you can now ask an AI agent to generate plays from your requirements, significantly reducing the time needed to create new Salesforce components.

Think of it as having an AI assistant that:

  • Searches for existing similar plays to prevent duplicates
  • Generates professional titles and descriptions
  • Creates Salesforce component code automatically
  • Handles file uploads reliably
  • Keeps you in control with approval workflows

Key Capabilities

1. Smart Duplicate Detection

Before creating a new play, Playground automatically searches for related plays and shows recommendations. This prevents duplicate work and encourages collaboration across your team.

2. AI-Generated Metadata

The system automatically generates:

  • Professional titles - Multiple suggestions based on your requirements
  • HTML descriptions - Rich, formatted descriptions ready for Playground
  • No manual typing needed

3. User Approval Workflow

You remain in full control:

  • Review all generated titles and descriptions
  • Amend them as needed
  • Explicitly approve before proceeding

4. Naming Convention Support

Define how component names should be formatted to match your coding standards:

  • Prefix strategy: ACME_AccountTrigger
  • Suffix strategy: AccountTrigger_v2
  • Namespace strategy: acme.AccountTrigger
  • Custom strategy: Your own naming pattern

5. Automatic Code Generation

From requirements like "Validate account phone numbers on insert/update", the system generates:

  • Apex Triggers with proper context
  • Apex Classes with business logic structure
  • XML metadata files with correct API versions
  • Proper directory structure (force-app/main/default/)

6. Reliable File Upload

Binary-stream file uploads (not base64) ensure:

  • Faster uploads
  • No timeout errors
  • Direct compatibility with Playground backend

Typical Workflow

Step 1: Define Requirements

Start by telling the AI agent what you want to build:

"Create a play that validates account phone numbers
on insert and update, supporting international format."

Step 2: Check for Duplicates

Playground MCP searches for existing similar plays and shows recommendations to prevent duplicate work.

Step 3: Review Generated Metadata

  • Title options: "Account Validator", "Phone Validation Engine", etc.
  • Description: Professional HTML-formatted description
  • You approve/amend both before proceeding

Step 4: Define Naming Convention

"Use ACME_ prefix for all components"

Ensures all generated components follow your organization's standards.

Step 5: Auto-Generate Structure

The system creates:

  • ACME_AccountTrigger.trigger + metadata XML
  • ACME_BusinessLogicHandler.cls + metadata XML
  • .playgignore file with best-practice patterns

Step 6: Upload & Create

  • Files are packaged and uploaded to Playground
  • Play is created with your generated content
  • You get the public URL

Time saved: From 30+ minutes → 2-3 minutes of interactive time

Getting Started

Step 1: Generate Playground Credentials

  1. Login to your Playground instance
  2. Navigate to Profile → App Passwords
  3. Click "Create New"
  4. Copy and securely store the generated token

Step 2: Get MCP Endpoint

The MCP server endpoint is:

https://mcp.playg.app/mcp

Step 3: Configure Your AI Agent

Provide these headers to your AI agent:

x-playground-url: https://your-playground-instance.com
x-playground-user: your-username
x-playground-token: <your-app-password-from-step-1>

Step 4: Start Creating Plays

Command your AI agent:

"Help me create a Salesforce play that validates
account phone numbers on insert/update using ACME_ prefix."

Note: Any AI agent supporting HTTP header authentication can connect to the MCP server.

System Requirements

  • Playground account with API access
  • An AI agent that supports HTTP-based MCP protocol
  • Basic knowledge of Salesforce components
  • Valid app password credentials

Limitations & Known Constraints

What MCP Does NOT Do

  • ❌ Deploy to Salesforce orgs (returns generated structure only)
  • ❌ Generate complex business logic (skeleton code provided; you fill TODO sections)
  • ❌ Validate against your existing Salesforce metadata
  • ❌ Handle advanced Salesforce patterns (custom objects, permission sets, etc.)

Current Scope

  • Supports creating new plays only (not updating existing)
  • Single-play creation per workflow
  • Tested up to 50MB file sizes
  • Requires manual code review before deployment

Best Practices

✅ Do's

  • ✅ Review all generated code before using
  • ✅ Test thoroughly in sandbox first
  • ✅ Use meaningful naming conventions
  • ✅ Provide detailed requirements to the AI agent
  • ✅ Report issues and provide feedback
  • ✅ Keep credentials secure

❌ Don'ts

  • ❌ Use generated code directly in production
  • ❌ Rely solely on auto-generated descriptions
  • ❌ Share credentials or auth tokens
  • ❌ Create plays for complex business logic without review
  • ❌ Bypass the approval workflow
  • ❌ Deploy without testing

Troubleshooting

"No related plays found" when they exist

  • Try simpler keywords
  • Check user permissions on Playground
  • Verify auth credentials are correct

Upload timeout errors

  • Reduce file size by using .playgignore
  • Check Playground backend status
  • Retry the upload

Component naming conflicts

  • Use unique prefix/suffix strategy
  • Check existing component names in Playground
  • Contact support if namespace issues persist

Generated code has TODOs

  • This is by design - you provide the business logic
  • Review and complete all TODO sections before deployment
  • Do NOT use auto-generated code as-is in production

FAQ

Q: Is MCP free?
A: Yes, MCP is included with your Playground subscription (Beta).

Q: What agents can connect?
A: Any AI agent supporting HTTP-based authentication and MCP protocol.

Q: What if generated code has issues?
A: You're responsible for reviewing and testing. Complete all TODO sections and validate in sandbox first.

Q: Can I use this in production?
A: Use at your own risk. We recommend thorough testing before production use.

Q: How do I report issues?
A: Visit the Playground Community to report issues and get support.

Support & Feedback

Report Issues

Visit the Playground Community to:

  • Report bugs and issues
  • Request features
  • Get help with setup
  • Share feedback

Provide Feedback

We actively collect feedback on:

  • Missing features you need
  • Confusing workflows
  • Generated code quality
  • Documentation gaps

Your input shapes the product roadmap.


Legal Disclaimer

⚠️ BETA FEATURE DISCLAIMER

This MCP Server is provided "AS-IS" in BETA and subject to change without notice. While we test thoroughly, we make no guarantees regarding:

  • Availability or uptime
  • Absence of bugs or errors
  • Compatibility with future versions
  • Generated code quality or security

Use at your own risk. You are fully responsible for reviewing, testing, and validating any generated code before use in production.