mcp-copilot-studio-server-generator — GitHub Copilot skill
Generates an MCP server and Power Platform connector files for Copilot Studio. Use it when building a custom connector with streamable HTTP.
npx skills add github/awesome-copilot --skill mcp-copilot-studio-server-generatorWhat mcp-copilot-studio-server-generator does
This skill directs the agent to create a Power Platform custom connector with MCP support: apiDefinition.swagger.json, apiProperties.json, script.csx, server code, tools, and resource handlers. It defines a POST /mcp endpoint, JSON-RPC 2.0 communication, and the x-ms-agentic-protocol: mcp-streamable-1.0 header.
Generated schemas avoid reference types, use one value per type field, and rely on primitive types. Enum input is handled as a validated string. Resources must be returned through tools because that is how Copilot Studio can access them. Prompts are not supported there.
Provide the server purpose, tools, resources, authentication method, host environment, and target APIs before generation. Install this skill if the target is Copilot Studio; its schema rules are too restrictive for a general MCP server.
What it helps with
- create a Power Platform custom connector
- add a
POST /mcpendpoint - avoid Copilot Studio schema restrictions
- define tools with primitive inputs
- return resources as tool outputs
Example prompts for the agent
- "Create an MCP server for customer data management and analysis through a CRM System REST API."
- "Add `searchCustomers`, `getCustomerDetails`, and `analyzeCustomerTrends` tools with oauth2."
- "Generate `apiDefinition.swagger.json` and `script.csx` for Azure Function."
How to install mcp-copilot-studio-server-generator
1Skills CLI (Vercel)
npx skills add github/awesome-copilot --skill mcp-copilot-studio-server-generator2GitHub CLI
gh skill install github/awesome-copilot mcp-copilot-studio-server-generator3Manually: put the files in place
.github/skills/mcp-copilot-studio-server-generator/SKILL.md1Skills CLI (Vercel)
npx skills add github/awesome-copilot --skill mcp-copilot-studio-server-generator -a claude-code2Manually: put the files in place
~/.claude/skills/mcp-copilot-studio-server-generator/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/mcp-copilot-studio-server-generator/
Manually: put the files in place
.agents/skills/mcp-copilot-studio-server-generator/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/mcp-copilot-studio-server-generator/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
Platform CLI
gemini skills install https://github.com/github/awesome-copilot --path skills/mcp-copilot-studio-server-generatorManually: put the files in place
.devin/skills/mcp-copilot-studio-server-generator/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set554
The whole set →Similar
Questions about mcp-copilot-studio-server-generator
How do I install mcp-copilot-studio-server-generator in GitHub Copilot?
Run npx skills add github/awesome-copilot --skill mcp-copilot-studio-server-generator. You can also use gh skill install github/awesome-copilot mcp-copilot-studio-server-generator.
What does mcp-copilot-studio-server-generator do?
The skill guides an agent to generate an MCP server and a Power Platform connector for Copilot Studio. Its output covers the connector schema, metadata, C# script, and MCP tool code.
Which Copilot Studio limits does the skill handle?
It avoids reference types, multiple type values, and enum inputs in tool schemas. Resources are exposed through tool outputs, while prompts are excluded because Copilot Studio does not support them.
Source text
SKILL.md · MIT
--- 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: 1. **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 2. **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 3. **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) 4. **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: 1. **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 2. **apiProperties.json** with: - Connector metadata and branding - Authentication configuration - Policy templates if needed 3. **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 4. **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 5. **Individual Tools** that: - Accept only primitive type inputs - Return structured outputs - Include resources as outputs when needed - Provide clear descriptions for Copilot Studio 6. **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 ```yaml 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 ```
© github · MIT · github/awesome-copilot