mcp-copilot-studio-server-generator
Helps your agent create an MCP server for Copilot Studio. It ensures the server works well with Copilot Studio and has the right rules.
What it does
This generator creates a 'connector' so that Microsoft Copilot Studio can communicate with other systems. It ensures communication is standardized and efficient, allowing Copilot Studio to use functions and data from elsewhere.
When to use it
- ✓When you want your Copilot Studio to access data from an external system.
- ✓When creating a virtual assistant that needs to interact with specific APIs.
- ✓To connect Copilot Studio to tools that require a standardized communication format.
Example of what to ask your AI
“Generate a connector so Copilot Studio can fetch customer information from our CRM and analyze sales trends.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
It creates configuration files and code that define how Copilot Studio sends and receives information, following a protocol called MCP. This includes defining the functions Copilot can call and how data should be structured.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add github/awesome-copilot --skill mcp-copilot-studio-server-generatorOr download just the file:
curl -L https://raw.githubusercontent.com/github/awesome-copilot/main/skills/mcp-copilot-studio-server-generator/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Power Platform MCP Connector Generator
Generate a complete Power Platform custom connector with Model Context Protocol (MCP) integration for Microsoft Copilot Studio. This prompt creates all necessary files following Power Platform connector standards with MCP streamable HTTP support.
Instructions
Create a complete MCP server implementation that:
Uses Copilot Studio MCP Pattern:
- Implement
x-ms-agentic-protocol: mcp-streamable-1.0 - Support JSON-RPC 2.0 communication protocol
- Provide streamable HTTP endpoint at
/mcp - Follow Power Platform connector structure
- Implement
Schema Compliance Requirements:
- NO reference types in tool inputs/outputs (filtered by Copilot Studio)
- Single type values only (not arrays of multiple types)
- Avoid enum inputs (interpreted as string, not enum)
- Use primitive types: string, number, integer, boolean, array, object
- Ensure all endpoints return full URIs
MCP Components to Include:
- Tools: Functions for the language model to call (✅ Supported in Copilot Studio)
- Resources: File-like data outputs from tools (✅ Supported in Copilot Studio - must be tool outputs to be accessible)
- Prompts: Predefined templates for specific tasks (❌ Not yet supported in Copilot Studio)
Implementation Structure:
/apiDefinition.swagger.json (Power Platform connector schema) /apiProperties.json (Connector metadata and configuration) /script.csx (Custom code transformations and logic) /server/ (MCP server implementation) /tools/ (Individual MCP tools) /resources/ (MCP resource handlers)
Context Variables
- Server Purpose: [Describe what the MCP server should accomplish]
- Tools Needed: [List of specific tools to implement]
- Resources: [Types of resources to provide]
- Authentication: [Auth method: none, api-key, oauth2]
- Host Environment: [Azure Function, Express.js, FastAPI, etc.]
- Target APIs: [External APIs to integrate with]
Expected Output
Generate:
apiDefinition.swagger.json with:
- Proper
x-ms-agentic-protocol: mcp-streamable-1.0 - MCP endpoint at POST
/mcp - Compliant schema definitions (no reference types)
- McpResponse and McpErrorResponse definitions
- Proper
apiProperties.json with:
- Connector metadata and branding
- Authentication configuration
- Policy templates if needed
script.csx with:
- Custom C# code for request/response transformations
- MCP JSON-RPC message handling logic
- Data validation and processing functions
- Error handling and logging capabilities
MCP Server Code with:
- JSON-RPC 2.0 request handler
- Tool registration and execution
- Resource management (as tool outputs)
- Proper error handling
- Copilot Studio compatibility checks
Individual Tools that:
- Accept only primitive type inputs
- Return structured outputs
- Include resources as outputs when needed
- Provide clear descriptions for Copilot Studio
Deployment Configuration for:
- Power Platform environment
- Copilot Studio agent integration
- Testing and validation
Validation Checklist
Ensure generated code:
- No reference types in schemas
- All type fields are single types
- Enum handling via string with validation
- Resources available through tool outputs
- Full URI endpoints
- JSON-RPC 2.0 compliance
- Proper x-ms-agentic-protocol header
- McpResponse/McpErrorResponse schemas
- Clear tool descriptions for Copilot Studio
- Generative Orchestration compatible
Example Usage
Server Purpose: Customer data management and analysis
Tools Needed:
- searchCustomers
- getCustomerDetails
- analyzeCustomerTrends
Resources:
- Customer profiles
- Analysis reports
Authentication: oauth2
Host Environment: Azure Function
Target APIs: CRM System REST API
FAQ
What is MCP?
MCP stands for Model Context Protocol. It's a communication standard that allows language models, like those used in Copilot Studio, to interact with external tools and services in a structured way.
What are 'reference types' and why avoid them?
Reference types are complex ways of defining data. Copilot Studio works best with simple data types (like text, number, boolean), so the generator removes or simplifies reference types to ensure compatibility.
What are 'tools' in this context?
Tools are like functions or commands that Copilot Studio can execute. The generator defines these tools so Copilot knows what actions it can perform in other systems.
Details
Original description by the author
Generate a complete MCP server implementation optimized for Copilot Studio integration with proper schema constraints and streamable HTTP support
repo: github/awesome-copilot
Popularity
- GitHub stars
- 40k
- Ranking position
- #5221
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
acquire-codebase-knowledge
Helps your agent understand and document an existing code project. It's useful for onboarding new people or getting an overview of the architecture.
github/awesome-copilot
acreadiness-assess
Enables your agent to assess a project's readiness for AI and generate a report. It's useful for understanding how well a project is prepared to use AI tools.
github/awesome-copilot
acreadiness-generate-instructions
Helps your agent create instructions for AI tools based on an assessment. It's useful for improving how AI interacts with code and closing identified gaps.
github/awesome-copilot
acreadiness-policy
Enables your agent to help define or apply policies for AI project assessment. It's useful for standardizing how projects are evaluated and ensuring compliance.
github/awesome-copilot
Similar skills
agent-architecture-audit
Makes your agent check if everything is working correctly. It finds and fixes problems in AI systems, ensuring they perform as expected.
affaan-m/ECC
agent-eval
Helps your agent compare different AI coding tools. It measures which one is faster, cheaper, and more reliable for specific tasks.
affaan-m/ECC
agent-harness-construction
Makes your agent better understand how to perform tasks. It optimizes the tools and instructions the agent uses to increase its chances of success.
affaan-m/ECC