Skip to main content
Glama
deenesjakoruzh
barissozudogru

gha-intel-mcp

by barissozudogru
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Hybrid

用于 GitHub Actions 工作流耗时分析、配置审计和计费洞察的 MCP 服务器。

工具

工具

描述

list_workflow_performance

计算最近工作流运行的平均、最小、最大和 p95 耗时统计。

analyze_workflow_config

评估工作流 YAML 中的缓存、并行度、并发、缓存、checkout 深度、超时、runner 固定、Docker 缓存和触发条件。

get_billing_usage

按 runner 类型返回 Actions 计费分钟数和估算成本，并给出各仓库的缓存用量。

Related MCP server: copilot-usage-mcp

环境要求

  • Node.js >= 18（使用原生 fetch）

  • 拥有 repo 和 read:org 权限的 GitHub 个人访问令牌

配置

提供三种传输模式，你可以选择适合自己部署情况的一种：

选项 A：stdio（本地，桌面客户端推荐）

服务器作为 MCP 客户端的子进程，通过 stdin/stdout 运行，无需网络端口。

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "gha-intel": {
      "command": "npx",
      "args": ["-y", "@barissozudogru/gha-intel-mcp"],
      "env": {
        "GITHUB_TOKEN": "ghp_your_token"
      }
    }
  }
}

Claude Code

claude mcp add gha-intel -e GITHUB_TOKEN=ghp_your_token -- npx -y @barissozudogru/gha-intel-mcp

Cursor

~/.cursor/mcp.json

{
  "mcpServers": {
    "gha-intel": {
      "command": "npx",
      "args": ["-y", "@barissozudogru/gha-intel-mcp"],
      "env": {
        "GITHUB_TOKEN": "ghp_your_token"
      }
    }
  }
}

Windsurf

~/.codeium/windsurf/mp_config.json

{
  "mcpServers": {
    "gha-intel": {
      "command": "npx",
      "args": ["-y", "@barissozudogru/gha-intel-mcp"],
      "env": {
        "GITHUB_TOKEN": "ghp_your_token"
      }
    }
  }
}

VS Code + Copilot

.vscode/mp.json（工作区）或用户设置

{
  "servers": {
    "gha-intel": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@barissozudogru/gha-intel-mcp"],
      "env": {
        "GITHUB_TOKEN": "ghp_your_token"
      }
    }
  }
}

C line

打开 C line 设置，进入 MCP Servers，然后添加：

{
  "mcpServers": {
    "gha-intel": {
      "command": "npx",
      "args": ["-y", "@barissozudogru/gha-intel-mcp"],
      "env": {
        "GITHUB_TOKEN": "ghp_your_token"
      }
    }
  }
}

Continue.dev

~/.continue/onfig.yaml

mcpServers:
  - name: gha-intel
    command: npx
    args:
      - -y
      - "@barissozudogru/gha-intel-mcp"
    env:
      GITHUB_TOKEN: ghp_your_token

Zed

~/.config/zed/settings.json

{
  "context_servers": {
    "gha-intel": {
      "command": {
        "path": "npx",
        "args": ["-y", "@barissozudogru/gha-intel-mcp"],
        "env": {
          "GITHUB_TOKEN": "ghp_your_token"
        }
      }
    }
  }
}

JetBrains (IntelliJ, PyCharm, WebStorm? 等)

前往 Settings > Tools > AI Assistant > MCP 并添加：

{
  "mcpServers": {
    "gha-intel": {
      "command": "npx",
      "args": ["-y", "@barissozudogru/gha-intel-mcp"],
      "env": {
        "GITHUB_TOKEN": "ghp_your_token"
      }
    }
  }
}

模式 B：HTTP（远程或云端客户端）

以 HTTP 模式启动服务器，并将客户端指向端点：

GITHUB_TOKEN=ghp_your_token npx @barissozudogru/gha-intel-mcp --http
# Server listens on http://0.0.0.0:3000/mcp
# Health check: http://localhost:3000/health

也可以通过环境变量进行设置，而不使用该参数：

TRANSPORT=http PORT=3000 GITHUB_TOKEN=ghp_your_token npx @barissozudogru/gha-intel-mcp

Cursor (HTTP)

~/.cursor/mp_json

{
  "mcpServers": {
    "gha-intel": {
      "url": "http://localhost:3000/mcp"
    }
  }
}

Code Code + Copilot (HTTP)

.vscode/mp_json

{
  "servers": {
    "gha-intel": {
      "type": "http",
      "url": "http://localhost:3000/mcp"
    }
  }
}

Windsurf (HTTP)

~/.codeium/windsurf/mp_config.json

{
  "mcpServers": {
    "gha-intel": {
      "serverUrl": "http://localhost:3000/mcp"
    }
  }
}

Continue.dev (HTTP)

~/.continue/config.yaml

mcpServers:
  - name: gha-intel
    url: http://localhost:3000/mcp

模式 C：Docker

docker build -t gha-intel-mcp .
docker run -p 3000:3000 -e GITHUB_TOKEN=ghp_your_token gha-intel-mcp

容器默认以 HTTP 模式启动。请将客户端指向 http://localhost:3000/mcp。

工具参考

list_workflow_perforance

Install Server
A
license - permissive license
A
quality
A
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
0dRelease cycle
5Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Tools

Related MCP Servers

  • copilot-usage-mcp

    tatsuyamiyazaki
    A
    license
    A
    quality
    C
    maintenance
    An MCP server that retrieves GitHub Copilot usage metrics and seat assignment data across Enterprise, Organization, and Team levels. It allows users to monitor code completions, chat activity, and active user counts through integrated tools.
    5
    1
    MIT

  • devflow-mcp

    boranesn
    A
    license
    Not graded
    quality
    D
    maintenance
    A production-ready MCP server that provides AI assistants with comprehensive GitHub developer tooling including PR analysis, code review, changelog generation, dependency auditing, commit summarization, and refactoring suggestions.
    13
    ISC

  • github-security-mcp

    badchars
    A
    license
    A
    quality
    D
    maintenance
    An MCP server that enables AI agents to perform comprehensive GitHub security audits across org settings, repositories, Actions workflows, secrets, supply chain, and access control using 39 tools and 45 checks.
    39
    521
    12
    MIT

View all related MCP servers

Related MCP Connectors

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/barissozudogru/gha-intel-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server