PluginBench
Skill
Official
Review
Audit score 70

power-platform-mcp-connector-suite

github/awesome-copilot

Generate Power Platform custom connectors with MCP integration for Copilot Studio, including schema validation and troubleshooting.

What is power-platform-mcp-connector-suite?

This skill generates complete Power Platform custom connectors with Model Context Protocol (MCP) integration for Microsoft Copilot Studio. It provides schema generation, validation for Copilot Studio compliance, and troubleshooting tools to ensure your connectors work correctly with MCP endpoints and avoid common integration issues.

  • Generate complete connector files (apiDefinition.swagger.json, apiProperties.json, script.csx, readme.md) with MCP protocol support
  • Validate schemas for Copilot Studio compliance (no reference types, single types, primitive types only)
  • Implement JSON-RPC 2.0 message handling and MCP endpoint transformations in C#
  • Diagnose and resolve MCP integration issues with Copilot Studio using CLI debugging
  • Support multiple generation modes: new connectors, schema validation, troubleshooting, hybrid connectors, certification prep, and OAuth hardening
  • Prepare connectors for Microsoft certification with complete metadata and security compliance

How to install power-platform-mcp-connector-suite

npx skills add https://github.com/github/awesome-copilot --skill power-platform-mcp-connector-suite
Prerequisites
  • Power Platform environment with Copilot Studio access
  • paconn CLI tool for schema validation
  • pac CLI for connector creation and updates
  • Azure Function or Express.js host environment for MCP server deployment
Claude Code
Cursor
Windsurf
Cline

How to use power-platform-mcp-connector-suite

  1. 1.Select a generation mode (Complete New Connector, Schema Validation, Integration Troubleshooting, Hybrid Connector, Certification Preparation, or OAuth Security Hardening)
  2. 2.Provide context variables: connector name, server purpose, tools needed, resources, authentication type, host environment, and target APIs
  3. 3.Review generated files: apiDefinition.swagger.json, apiProperties.json, script.csx, and readme.md
  4. 4.Run validation: execute `paconn validate --api-def apiDefinition.swagger.json` to check Copilot Studio compliance
  5. 5.Deploy the connector using pac CLI: `pac connector create` or `pac connector update`
  6. 6.Test MCP endpoints and tool execution in Copilot Studio, then iterate on any schema or transformation issues

Use cases

Good for
  • Build a new MCP connector for customer analytics with tools to search customers and analyze trends
  • Validate an existing Power Platform connector schema to ensure Copilot Studio compatibility
  • Debug connection failures between a custom connector and Copilot Studio by checking protocol headers and type definitions
  • Add MCP capabilities to an existing Power Platform connector without rebuilding from scratch
  • Prepare a connector for Microsoft certification submission with OAuth 2.0 security hardening and complete documentation
Who it's for
  • Power Platform developers building custom connectors for Copilot Studio
  • Enterprise architects integrating external APIs with Microsoft Copilot
  • DevOps engineers managing connector deployment and validation pipelines
  • Security teams implementing OAuth 2.0 and MCP security best practices

power-platform-mcp-connector-suite FAQ

What MCP capabilities does Copilot Studio currently support?

Copilot Studio currently supports Tools (functions the LLM can call with user approval) and Resources (file-like data that agents can read as tool outputs). Prompts are not yet supported but the skill prepares for future support.

Why are reference types ($ref) not allowed in Copilot Studio connectors?

Copilot Studio requires primitive types only in tool inputs and outputs for direct schema compliance. Reference types must be resolved to their primitive definitions (string, number, integer, boolean, array, object) to avoid filtering and ensure tools are available to agents.

How do I troubleshoot tools being filtered out of Copilot Studio?

Tools are typically filtered due to reference types or array type definitions. Remove all $ref entries and ensure all type fields contain single primitive types, not arrays like ["string", "number"]. Validate with `paconn validate` before deployment.

What authentication methods are supported for MCP connectors?

The skill supports none, api-key, oauth2, and basic authentication. For production use, OAuth 2.0 with MCP security hardening (token validation, state parameter protection, HTTPS enforcement) is recommended to prevent confused deputy attacks.

Can I add MCP capabilities to an existing Power Platform connector?

Yes, use Mode 4 (Hybrid Connector) to add MCP capabilities to an existing connector. This adds the MCP endpoint, JSON-RPC handling, and validation workflows while preserving your existing connector structure and authentication.

Full instructions (SKILL.md)

Source of truth, from github/awesome-copilot.


name: power-platform-mcp-connector-suite description: 'Generate complete Power Platform custom connector with MCP integration for Copilot Studio - includes schema generation, troubleshooting, and validation'

Power Platform MCP Connector Suite

Generate comprehensive Power Platform custom connector implementations with Model Context Protocol integration for Microsoft Copilot Studio.

MCP Capabilities in Copilot Studio

Currently Supported:

  • ✅ Tools: Functions that the LLM can call (with user approval)
  • ✅ Resources: File-like data that agents can read (must be tool outputs)

Not Yet Supported:

  • ❌ Prompts: Pre-written templates (prepare for future support)

Connector Generation

Create complete Power Platform connector with:

Core Files:

  • apiDefinition.swagger.json with x-ms-agentic-protocol: mcp-streamable-1.0
  • apiProperties.json with connector metadata and authentication
  • script.csx with custom C# transformations for MCP JSON-RPC handling
  • readme.md with connector documentation

MCP Integration:

  • POST /mcp endpoint for JSON-RPC 2.0 communication
  • McpResponse and McpErrorResponse schema definitions
  • Copilot Studio constraint compliance (no reference types, single types)
  • Resource integration as tool outputs (Resources and Tools supported; Prompts not yet supported)

Schema Validation & Troubleshooting

Validate schemas for Copilot Studio compliance:

  • ✅ No reference types ($ref) in tool inputs/outputs
  • ✅ Single type values only (not ["string", "number"])
  • ✅ Primitive types: string, number, integer, boolean, array, object
  • ✅ Resources as tool outputs, not separate entities
  • ✅ Full URIs for all endpoints

Common issues and fixes:

  • Tools filtered → Remove reference types, use primitives
  • Type errors → Single types with validation logic
  • Resources unavailable → Include in tool outputs
  • Connection failures → Verify x-ms-agentic-protocol header

Context Variables

  • Connector Name: [Display name for the connector]
  • Server Purpose: [What the MCP server should accomplish]
  • Tools Needed: [List of MCP tools to implement]
  • Resources: [Types of resources to provide]
  • Authentication: [none, api-key, oauth2, basic]
  • Host Environment: [Azure Function, Express.js, etc.]
  • Target APIs: [External APIs to integrate with]

Generation Modes

Mode 1: Complete New Connector

Generate all files for a new Power Platform MCP connector from scratch, including CLI validation setup.

Mode 2: Schema Validation

Analyze and fix existing schemas for Copilot Studio compliance using paconn and validation tools.

Mode 3: Integration Troubleshooting

Diagnose and resolve MCP integration issues with Copilot Studio using CLI debugging tools.

Mode 4: Hybrid Connector

Add MCP capabilities to existing Power Platform connector with proper validation workflows.

Mode 5: Certification Preparation

Prepare connector for Microsoft certification submission with complete metadata and validation compliance.

Mode 6: OAuth Security Hardening

Implement OAuth 2.0 authentication enhanced with MCP security best practices and advanced token validation.

Expected Output

1. apiDefinition.swagger.json

  • Swagger 2.0 format with Microsoft extensions
  • MCP endpoint: POST /mcp with proper protocol header
  • Compliant schema definitions (primitive types only)
  • McpResponse/McpErrorResponse definitions

2. apiProperties.json

  • Connector metadata and branding (iconBrandColor required)
  • Authentication configuration
  • Policy templates for MCP transformations

3. script.csx

  • JSON-RPC 2.0 message handling
  • Request/response transformations
  • MCP protocol compliance logic
  • Error handling and validation

4. Implementation guidance

  • Tool registration and execution patterns
  • Resource management strategies
  • Copilot Studio integration steps
  • Testing and validation procedures

Validation Checklist

Technical Compliance

  • x-ms-agentic-protocol: mcp-streamable-1.0 in MCP endpoint
  • No reference types in any schema definitions
  • All type fields are single types (not arrays)
  • Resources included as tool outputs
  • JSON-RPC 2.0 compliance in script.csx
  • Full URI endpoints throughout
  • Clear descriptions for Copilot Studio agents
  • Authentication properly configured
  • Policy templates for MCP transformations
  • Generative Orchestration compatibility

CLI Validation

  • paconn validate: paconn validate --api-def apiDefinition.swagger.json passes without errors
  • pac CLI ready: Connector can be created/updated with pac connector create/update
  • Script validation: script.csx passes automatic validation during pac CLI upload
  • Package validation: ConnectorPackageValidator.ps1 runs successfully

OAuth and Security Requirements

  • OAuth 2.0 Enhanced: Standard OAuth 2.0 with MCP security best practices implementation
  • Token Validation: Implement token audience validation to prevent passthrough attacks
  • Custom Security Logic: Enhanced validation in script.csx for MCP compliance
  • State Parameter Protection: Secure state parameters for CSRF prevention
  • HTTPS Enforcement: All production endpoints use HTTPS only
  • MCP Security Practices: Implement confused deputy attack prevention within OAuth 2.0

Certification Requirements

  • Complete metadata: settings.json with product and service information
  • Icon compliance: PNG format, 230x230 or 500x500 dimensions
  • Documentation: Certification-ready readme with comprehensive examples
  • Security compliance: OAuth 2.0 enhanced with MCP security practices, privacy policy
  • Authentication flow: OAuth 2.0 with custom security validation properly configured

Example Usage

Mode: Complete New Connector
Connector Name: Customer Analytics MCP
Server Purpose: Customer data analysis and insights
Tools Needed:
  - searchCustomers: Find customers by criteria
  - getCustomerProfile: Retrieve detailed customer data
  - analyzeCustomerTrends: Generate trend analysis
Resources:
  - Customer profiles (JSON data)
  - Analysis reports (structured data)
Authentication: oauth2
Host Environment: Azure Function
Target APIs: CRM REST API