mcp-copilot-studio-server-generator
github/awesome-copilot
Generate MCP servers optimized for Copilot Studio with proper schema constraints and streamable HTTP support.
What is mcp-copilot-studio-server-generator?
This skill generates complete Model Context Protocol (MCP) server implementations designed for Microsoft Copilot Studio integration. It creates Power Platform custom connectors with JSON-RPC 2.0 communication, schema compliance (no reference types, primitive types only), and streamable HTTP endpoints following Copilot Studio's agentic protocol standards.
- Generate apiDefinition.swagger.json with x-ms-agentic-protocol: mcp-streamable-1.0 and MCP endpoint configuration
- Create apiProperties.json with connector metadata, branding, and authentication setup
- Produce script.csx with C# transformations, JSON-RPC message handling, and data validation logic
- Build MCP server code with JSON-RPC 2.0 request handlers, tool registration, and resource management
- Generate individual tool implementations with primitive-type inputs and structured outputs
- Provide deployment configuration for Power Platform and Copilot Studio agent integration
How to install mcp-copilot-studio-server-generator
npx skills add https://github.com/github/awesome-copilot --skill mcp-copilot-studio-server-generator- Understanding of Model Context Protocol (MCP) and JSON-RPC 2.0
- Familiarity with Power Platform connector structure and Swagger/OpenAPI specifications
- Knowledge of the target external APIs to integrate
- Clarity on authentication method (none, API key, or OAuth2)
How to use mcp-copilot-studio-server-generator
- 1.Define context variables: server purpose, required tools, resources, authentication method, host environment, and target APIs
- 2.Run the skill to generate the complete MCP server package with all required files
- 3.Review the generated apiDefinition.swagger.json to ensure schema compliance (no reference types, single type values, primitive types only)
- 4.Customize script.csx with your specific request/response transformation logic and validation rules
- 5.Implement individual tool handlers in the /tools directory with proper input/output schemas
- 6.Test the MCP endpoint at POST /mcp for JSON-RPC 2.0 compliance and Copilot Studio compatibility
- 7.Deploy to your chosen host environment (Azure Function, Express.js, FastAPI, etc.)
- 8.Register the connector in Power Platform and configure Copilot Studio agent integration
Use cases
- Building custom connectors for CRM systems to enable Copilot Studio agents to search and analyze customer data
- Creating MCP servers that integrate external APIs with proper schema compliance for agentic orchestration
- Generating tools for data transformation and analysis that output resources accessible within Copilot Studio workflows
- Setting up authentication-enabled connectors (API key, OAuth2) for secure third-party API integration
- Developing multi-tool MCP implementations where resources are exposed as tool outputs for downstream use
- Power Platform developers building Copilot Studio agents
- Enterprise architects integrating external APIs with Microsoft Copilot
- AI engineers implementing custom connectors with schema compliance requirements
- Teams deploying MCP servers to Azure Functions or other host environments
mcp-copilot-studio-server-generator FAQ
Avoid reference types in tool inputs/outputs, use only single type values (not arrays of multiple types), avoid enum inputs (use string with validation instead), and ensure all endpoints return full URIs. Only primitive types (string, number, integer, boolean, array, object) are supported.
Resources must be provided as outputs from tools. They are not directly supported as standalone MCP components in Copilot Studio, so any resource data should be returned within tool output schemas.
This header (set to mcp-streamable-1.0) identifies the connector as an MCP server with streamable HTTP support. It enables Copilot Studio to properly handle the JSON-RPC 2.0 communication protocol and MCP endpoint at POST /mcp.
Prompts are not yet supported in Copilot Studio, so focus on implementing tools and resources instead. Tools are fully supported and can be called by the language model.
The generator supports none (no authentication), API key, and OAuth2 authentication methods. Configure your preferred method in the context variables and apiProperties.json.
Full instructions (SKILL.md)
Source of truth, from github/awesome-copilot.
name: mcp-copilot-studio-server-generator description: 'Generate a complete MCP server implementation optimized for Copilot Studio integration with proper schema constraints and streamable HTTP support'
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
Related skills
More from github/awesome-copilot and the wider catalog.

mcp-create-adaptive-cards
Add Adaptive Card response templates to MCP API plugins for rich visual output in Microsoft 365 Copilot.

mcp-create-declarative-agent
Create declarative agents for Microsoft 365 Copilot by integrating MCP servers with authentication and tool selection.

mcp-deploy-manage-agents
Guidance for deploying, managing, and governing MCP-based declarative agents in the Microsoft 365 admin center.

mcp-security-audit
|

meeting-minutes
Generate concise, actionable meeting minutes with decisions, action items, and owners for internal meetings under 60 minutes.

memory-merger
Consolidate domain learnings from memory files into instruction files with zero knowledge loss.