Skip to main content
skill GitHub Copilot official · GitHub

mcp-create-declarative-agent — GitHub Copilot skill: MCP agent

This skill builds a declarative agent for Microsoft 365 Copilot and connects it to an MCP server. Use it when the agent needs selected tools from an external system.

Install into GitHub Copilot · Skills CLI (Vercel) All methods and platforms ↓
npx skills add github/awesome-copilot --skill mcp-create-declarative-agent
Open on GitHub

What mcp-create-declarative-agent does

The skill scaffolds a declarative agent with Microsoft 365 Agents Toolkit, adds an MCP action, and imports selected server tools. It helps configure manifest.json, declarativeAgent.json, ai-plugin.json, and .vscode/mcp.json, including response semantics for mapping API fields.

The MCP server needs metadata, a tool listing, and a tool execution endpoint. Authentication can use OAuth 2.0 or SSO, with credentials placed in .env.local or .env.dev. You also need the MCP server address and a clear list of functions the agent should expose.

Install this when you are building a Microsoft 365 Copilot agent around an MCP server and need controlled tool selection. It is a poor fit for an agent that does not use MCP.

What it helps with

  • build a declarative agent for Microsoft 365 Copilot
  • connect an MCP server to the agent
  • select tools to import from MCP
  • configure OAuth 2.0 or SSO
  • map API response fields for the agent

Example prompts for the agent

  • Create a Microsoft 365 Copilot declarative agent from an MCP server and import only the required tools.
  • Configure `ai-plugin.json`, `declarativeAgent.json`, and OAuth 2.0 for this MCP integration.
  • Validate tool imports, response semantics, and local testing with Microsoft 365 Agents Toolkit.

How to install mcp-create-declarative-agent

1Skills CLI (Vercel)

npx skills add github/awesome-copilot --skill mcp-create-declarative-agent

2GitHub CLI

gh skill install github/awesome-copilot mcp-create-declarative-agent

3Manually: put the files in place

.github/skills/mcp-create-declarative-agent/SKILL.md

From the same set554

The whole set →
git-commit official github This skill reviews Git changes, stages related files, and creates Conventional Commits. Use it when you want an agent to make one commit or split work into separate commits. GitHub Copilot 47,165installs excalidraw-diagram-generator official github Turn a plain-language description into an Excalidraw diagram. Useful for mapping processes, system structure, and relationships between entities. GitHub Copilot 31,639installs multi-stage-dockerfile official github This skill guides GitHub Copilot in writing multi-stage Dockerfiles for different languages and frameworks. Use it when the final runtime image should contain fewer build dependencies. GitHub Copilot 29,688installs documentation-writer official github Skill that turns the agent into a technical writer following the Diátaxis framework: tutorials, how-to guides, reference, and explanation. Proposes structure before writing. GitHub Copilot 27,757installs prd official github Turns a feature idea into a structured PRD with user stories, technical requirements, and risks. Use it when planning a software feature or an AI-powered one. GitHub Copilot 24,035installs refactor official github This skill reshapes existing code without changing its external behavior. Use it for gradual cleanup of large functions, duplication, weak types, and code smells. GitHub Copilot 22,321installs java-springboot official github Gives GitHub Copilot Spring Boot development practices, from project layout to tests and security. Use it when writing or reviewing Java application code. GitHub Copilot 21,272installs create-readme official github This skill reviews a project and creates a structured README.md. Use it when the repository needs clear documentation based on its actual files and code. GitHub Copilot 19,081installs

Similar

session-report official Anthropic Generates an interactive HTML report on token usage, cache performance, subagents, and heavy prompts from Claude Code transcripts. Claude Code 3,676installs claude-certification rohitg00 Walks you through one of four Claude certification tracks: teaches the lesson, runs the lab, checks your artifacts. Useful when you are preparing for an exam and want a tutor instead of a reading list. Claude Code CX Codex Cursor +1 3,300installs prompt-master nidhinjs This skill writes and improves prompts for a named AI tool. Use it when a rough request needs to become a ready-to-paste prompt for Claude Code, Cursor, or another supported tool. Claude Code CX Codex Cursor +1 3,900installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. Claude Code CX Codex Cursor +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. Claude Code Claude.ai 130,949installs subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. Claude Code CX Codex 237,746installs

Questions about mcp-create-declarative-agent

How do I install mcp-create-declarative-agent in GitHub Copilot?

Run npx skills add github/awesome-copilot --skill mcp-create-declarative-agent, then use .github/skills/mcp-create-declarative-agent/SKILL.md.

What does mcp-create-declarative-agent do?

It guides GitHub Copilot through creating a Microsoft 365 Copilot declarative agent, connecting an MCP server, selecting tools, and configuring the generated files.

Which authentication methods does it support?

The configuration supports OAuth 2.0 and SSO. OAuth uses a reference ID and client settings, with credentials stored in .env.local or .env.dev.

Source text

SKILL.md · MIT
---
name: mcp-create-declarative-agent
description: 'Skill converted from mcp-create-declarative-agent.prompt.md'
---

````prompt
---
mode: 'agent'
tools: ['changes', 'search/codebase', 'edit/editFiles', 'problems']
description: 'Create a declarative agent for Microsoft 365 Copilot by integrating an MCP server with authentication, tool selection, and configuration'
model: 'gpt-4.1'
tags: [mcp, m365-copilot, declarative-agent, model-context-protocol, api-plugin]
---

# Create MCP-based Declarative Agent for Microsoft 365 Copilot

Create a complete declarative agent for Microsoft 365 Copilot that integrates with a Model Context Protocol (MCP) server to access external systems and data.

## Requirements

Generate the following project structure using Microsoft 365 Agents Toolkit:

### Project Setup
1. **Scaffold declarative agent** via Agents Toolkit
2. **Add MCP action** pointing to MCP server
3. **Select tools** to import from MCP server
4. **Configure authentication** (OAuth 2.0 or SSO)
5. **Review generated files** (manifest.json, ai-plugin.json, declarativeAgent.json)

### Key Files Generated

**appPackage/manifest.json** - Teams app manifest with plugin reference:
```json
{
  "$schema": "https://developer.microsoft.com/json-schemas/teams/vDevPreview/MicrosoftTeams.schema.json",
  "manifestVersion": "devPreview",
  "version": "1.0.0",
  "id": "...",
  "developer": {
    "name": "...",
    "websiteUrl": "...",
    "privacyUrl": "...",
    "termsOfUseUrl": "..."
  },
  "name": {
    "short": "Agent Name",
    "full": "Full Agent Name"
  },
  "description": {
    "short": "Short description",
    "full": "Full description"
  },
  "copilotAgents": {
    "declarativeAgents": [
      {
        "id": "declarativeAgent",
        "file": "declarativeAgent.json"
      }
    ]
  }
}
```

**appPackage/declarativeAgent.json** - Agent definition:
```json
{
  "$schema": "https://aka.ms/json-schemas/copilot/declarative-agent/v1.0/schema.json",
  "version": "v1.0",
  "name": "Agent Name",
  "description": "Agent description",
  "instructions": "You are an assistant that helps with [specific domain]. Use the available tools to [capabilities].",
  "capabilities": [
    {
      "name": "WebSearch",
      "websites": [
        {
          "url": "https://learn.microsoft.com"
        }
      ]
    },
    {
      "name": "MCP",
      "file": "ai-plugin.json"
    }
  ]
}
```

**appPackage/ai-plugin.json** - MCP plugin manifest:
```json
{
  "schema_version": "v2.1",
  "name_for_human": "Service Name",
  "description_for_human": "Description for users",
  "description_for_model": "Description for AI model",
  "contact_email": "[email protected]",
  "namespace": "serviceName",
  "capabilities": {
    "conversation_starters": [
      {
        "text": "Example query 1"
      }
    ]
  },
  "functions": [
    {
      "name": "functionName",
      "description": "Function description",
      "capabilities": {
        "response_semantics": {
          "data_path": "$",
          "properties": {
            "title": "$.title",
            "subtitle": "$.description"
          }
        }
      }
    }
  ],
  "runtimes": [
    {
      "type": "MCP",
      "spec": {
        "url": "https://api.service.com/mcp/"
      },
      "run_for_functions": ["functionName"],
      "auth": {
        "type": "OAuthPluginVault",
        "reference_id": "${{OAUTH_REFERENCE_ID}}"
      }
    }
  ]
}
```

**/.vscode/mcp.json** - MCP server configuration:
```json
{
  "serverUrl": "https://api.service.com/mcp/",
  "pluginFilePath": "appPackage/ai-plugin.json"
}
```

## MCP Server Integration

### Supported MCP Endpoints
The MCP server must provide:
- **Server metadata** endpoint
- **Tools listing** endpoint (exposes available functions)
- **Tool execution** endpoint (handles function calls)

### Tool Selection
When importing from MCP:
1. Fetch available tools from server
2. Select specific tools to include (for security/simplicity)
3. Tool definitions are auto-generated in ai-plugin.json

### Authentication Types

**OAuth 2.0 (Static Registration)**
```json
"auth": {
  "type": "OAuthPluginVault",
  "reference_id": "${{OAUTH_REFERENCE_ID}}",
  "authorization_url": "https://auth.service.com/authorize",
  "client_id": "${{CLIENT_ID}}",
  "client_secret": "${{CLIENT_SECRET}}",
  "scope": "read write"
}
```

**Single Sign-On (SSO)**
```json
"auth": {
  "type": "SSO"
}
```

## Response Semantics

### Define Data Mapping
Use `response_semantics` to extract relevant fields from API responses:

```json
"capabilities": {
  "response_semantics": {
    "data_path": "$.results",
    "properties": {
      "title": "$.name",
      "subtitle": "$.description",
      "url": "$.link"
    }
  }
}
```

### Add Adaptive Cards (Optional)
See the `mcp-create-adaptive-cards` prompt for adding visual card templates.

## Environment Configuration

Create `.env.local` or `.env.dev` for credentials:

```env
OAUTH_REFERENCE_ID=your-oauth-reference-id
CLIENT_ID=your-client-id
CLIENT_SECRET=your-client-secret
```

## Testing & Deployment

### Local Testing
1. **Provision** agent in Agents Toolkit
2. **Start debugging** to sideload in Teams
3. Test in Microsoft 365 Copilot at https://m365.cloud.microsoft/chat
4. Authenticate when prompted
5. Query the agent using natural language

### Validation
- Verify tool imports in ai-plugin.json
- Check authentication configuration
- Test each exposed function
- Validate response data mapping

## Best Practices

### Tool Design
- **Focused functions**: Each tool should do one thing well
- **Clear descriptions**: Help the model understand when to use each tool
- **Minimal scoping**: Only import tools the agent needs
- **Descriptive names**: Use action-oriented function names

### Security
- **Use OAuth 2.0** for production scenarios
- **Store secrets** in environment variables
- **Validate inputs** on the MCP server side
- **Limit scopes** to minimum required permissions
- **Use reference IDs** for OAuth registration

### Instructions
- **Be specific** about the agent's purpose and capabilities
- **Define behavior** for both successful and error scenarios
- **Reference tools** explicitly in instructions when applicable
- **Set expectations** for users about what the agent can/cannot do

### Performance
- **Cache responses** when appropriate on MCP server
- **Batch operations** where possible
- **Set timeouts** for long-running operations
- **Paginate results** for large datasets

## Common MCP Server Examples

### GitHub MCP Server
```
URL: https://api.githubcopilot.com/mcp/
Tools: search_repositories, search_users, get_repository
Auth: OAuth 2.0
```

### Jira MCP Server
```
URL: https://your-domain.atlassian.net/mcp/
Tools: search_issues, create_issue, update_issue
Auth: OAuth 2.0
```

### Custom Service
```
URL: https://api.your-service.com/mcp/
Tools: Custom tools exposed by your service
Auth: OAuth 2.0 or SSO
```

## Workflow

Ask the user:
1. What MCP server are you integrating with (URL)?
2. What tools should be exposed to Copilot?
3. What authentication method does the server support?
4. What should the agent's primary purpose be?
5. Do you need response semantics or Adaptive Cards?

Then generate:
- Complete appPackage/ structure (manifest.json, declarativeAgent.json, ai-plugin.json)
- mcp.json configuration
- .env.local template
- Provisioning and testing instructions

## Troubleshooting

### MCP Server Not Responding
- Verify server URL is correct
- Check network connectivity
- Validate MCP server implements required endpoints

### Authentication Fails
- Verify OAuth credentials are correct
- Check reference ID matches registration
- Confirm scopes are requested properly
- Test OAuth flow independently

### Tools Not Appearing
- Ensure mcp.json points to correct server
- Verify tools were selected during import
- Check ai-plugin.json has correct function definitions
- Re-fetch actions from MCP if server changed

### Agent Not Understanding Queries
- Review instructions in declarativeAgent.json
- Check function descriptions are clear
- Verify response_semantics extract correct data
- Test with more specific queries

````

© github · MIT · github/awesome-copilot

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor