copilot-usage-mcp
Interfaces with the GitHub API to retrieve Enterprise and Organization-level data, including seat assignments and integration summaries.
Enables retrieval of daily usage metrics, chat activity, active user counts, and detailed breakdowns by language and editor for GitHub Copilot at the Enterprise, Organization, and Team levels.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@copilot-usage-mcp Show me a summary of GitHub Copilot usage and seat assignments for my organization"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
copilot-usage-mcp
GitHub Copilot の利用状況メトリクスを取得する MCP (Model Context Protocol) サーバーです。
Enterprise、Organization、Team レベルでの Copilot 使用状況データを MCP ツールとして提供します。
提供ツール
ツール名 | 説明 |
| Enterprise 全体の日次 Copilot 利用メトリクス |
| Organization の日次 Copilot 利用メトリクス |
| Team の日次 Copilot 利用メトリクス |
| Organization の Copilot シート割り当て情報 |
| Enterprise / Org / Seats の統合サマリー |
各ツールは、コード補完数・Chat 利用状況・アクティブユーザー数・言語 / エディタ別の内訳などを取得できます。
Related MCP server: copilot-status-mcp
セットアップ
前提条件
Node.js 18+
GitHub Personal Access Token(Copilot メトリクス API へのアクセス権限が必要)
インストール
npm install
npm run build環境変数
コマンドライン引数または環境変数で以下を設定してください(.env ファイルは読み込まれません)。
変数名 | 必須 | 説明 |
| Yes | GitHub Personal Access Token |
| No | Enterprise slug |
| No | Organization 名 |
| No | キャッシュディレクトリ(デフォルト: |
MCP クライアントへの設定
Claude Desktop の場合、claude_desktop_config.json に以下を追加します。
{
"mcpServers": {
"copilot-usage": {
"command": "node",
"args": ["path/to/copilot-usage-mcp/dist/index.js"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_xxxxxxxxxxxx",
"GITHUB_ENTERPRISE": "your-enterprise",
"GITHUB_ORG": "your-org"
}
}
}
}開発
# TypeScript のウォッチモードで開発
npm run dev
# テスト実行
npm test
# テストのウォッチモード
npm run test:watchライセンス
Available Tools
5 toolsget_copilot_metrics_for_enterpriseA
Get daily Copilot usage metrics for the entire GitHub Enterprise (code completions, chat usage, active users, language/editor breakdown)
Inputs: enterprise, since, until, force_refresh.
get_copilot_metrics_for_orgA
Get daily Copilot usage metrics for a GitHub Organization (code completions, chat usage, active users, language/editor breakdown)
Inputs: org, since, until, force_refresh.
get_copilot_metrics_for_teamC
Get daily Copilot usage metrics for a specific team within an Organization
Inputs: team_slug (required), org, since, until, +1 more.
get_copilot_seat_assignmentsC
Get Copilot seat assignments for an Organization (user list with last activity date, editor info, plan type)
Inputs: org, force_refresh.
get_copilot_usage_summaryA
Get a combined summary of Copilot usage across Enterprise, Organization, and seat assignments. Optionally include team-level metrics.
Inputs: since, until, team_slug, force_refresh.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose targeting different aspects of Copilot usage data. The enterprise, organization, team, seat assignments, and summary tools all operate at different scopes with no functional overlap, making tool selection unambiguous.
All tools follow a perfect 'get_copilot_[noun]_[preposition]_[target]' pattern with consistent snake_case throughout. The naming convention is highly predictable and readable across all five tools.
Five tools is an ideal number for this focused domain of Copilot usage analytics. Each tool serves a distinct reporting function without redundancy, providing comprehensive coverage while maintaining a manageable interface.
The toolset provides complete coverage for Copilot usage reporting across all relevant scopes (enterprise, organization, team, seat assignments) with a convenient summary tool. There are no obvious gaps in the analytics surface for this specific domain.
Maintenance
Related MCP Connectors
GitHub Copilot MCP: code, repo, PR, workflow tools for AI assistants.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
Analytics for MCP servers. Query your tool calls, first-call success, retries and schema cost.
Create, deploy, and operate MCP servers directly from your GitHub repositories.
Related MCP Servers
- AlicenseAqualityFmaintenanceAn MCP server that retrieves current GitHub Copilot usage data, including quotas, limits, and usage statistics. It allows AI agents to monitor premium interaction status and detailed account usage via raw or formatted summaries.39 npmMIT
- AlicenseAqualityCmaintenanceMCP server to check GitHub Copilot quota, rate-limit status, and reset times from any MCP client.132 npmMIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides tools for interacting with the GitHub API, enabling AI assistants to query repositories, pull requests, issues, commits, users, and more.497 npmISC
- AlicenseNot gradedqualityDmaintenanceExposes GitHub Copilot premium request usage as an MCP tool, providing a breakdown by model and cost.MIT