power-platform-mcp-connector-suite

por github

Gere conector personalizado completo do Power Platform com integração MCP para o Copilot Studio - inclui geração de esquema, solução de problemas e validação

npx skills add https://github.com/github/awesome-copilot --skill power-platform-mcp-connector-suite

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

Mais skills de github

console-rendering
github
Instruções para usar o sistema de renderização de console baseado em tags de struct em Go
official
acquire-codebase-knowledge
github
Use esta habilidade quando o usuário solicitar explicitamente mapear, documentar ou integrar-se a uma base de código existente. Ative para comandos como "mapeie esta base de código", "documente…
official
acreadiness-assess
github
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc…
official
acreadiness-generate-instructions
github
Gera arquivos de instrução de agente de IA personalizados através do comando de instruções do AgentRC. Produz .github/copilot-instructions.md (padrão, recomendado para o Copilot no VS…
official
acreadiness-policy
github
Ajude o usuário a escolher, escrever ou aplicar uma política AgentRC. Políticas personalizam a pontuação de prontidão desabilitando verificações irrelevantes, substituindo impacto/nível, definindo…
official
add-educational-comments
github
Adiciona comentários educacionais a arquivos de código para transformá-los em recursos de aprendizado eficazes. Adapta a profundidade e o tom das explicações para três níveis de conhecimento configuráveis: iniciante, intermediário e avançado. Solicita automaticamente um arquivo caso nenhum seja fornecido, com correspondência de lista numerada para seleção rápida. Expande arquivos em até 125% usando apenas comentários educacionais (limite máximo: 400 novas linhas; 300 para arquivos com mais de 1.000 linhas). Preserva a codificação do arquivo, o estilo de indentação, a correção sintática e...
official
adobe-illustrator-scripting
github
Escreva, depure e otimize scripts de automação do Adobe Illustrator usando ExtendScript (JavaScript/JSX). Use ao criar ou modificar scripts que manipulam…
official
agent-governance
github
Políticas declarativas, classificação de intenção e trilhas de auditoria para controlar o acesso e comportamento de ferramentas de agentes de IA. Políticas de governança componíveis definem ferramentas permitidas/bloqueadas, filtros de conteúdo, limites de taxa e requisitos de aprovação — armazenados como configuração, não código. A classificação semântica de intenção detecta prompts perigosos (exfiltração de dados, escalada de privilégio, injeção de prompt) antes da execução da ferramenta usando sinais baseados em padrões. O decorador de governança em nível de ferramenta aplica políticas em funções...
official