power-platform-mcp-connector-suite
Generate complete Power Platform custom connector with MCP integration for Copilot Studio - includes schema generation, troubleshooting, and validation
What this skill does
# 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 ```yaml 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 ```
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.