Bijon Portfolio MCP Server

Bijon Portfolio MCP Server

Exposes a personal portfolio's resume, projects, skills, certifications, and live GitHub repositories as tools for AI assistants to query via natural language.

Category
访问服务器

README

🔌 Bijon Portfolio MCP Server

A Node.js & TypeScript-based Model Context Protocol (MCP) server that exposes my resume, portfolio projects, certifications, skills, and live GitHub repositories as tools. This allows AI assistants (like Claude Desktop) to query my professional background, projects, and experiences dynamically using natural language.


🚀 Features & Exposed Tools

The server registers the following tools with the MCP client:

  1. getProfile: Exposes core bio, contact information, education history, work/internship experiences, volunteering, and social links.
  2. getProjects: Lists curated portfolio projects (both professional and academic), with support for filtering by specific tech stacks (e.g. React, Laravel, Node.js).
  3. getSkills: Lists structured technical skills categorized by programming languages, frameworks, and developer tools.
  4. getCertificates: Lists professional and academic certifications (e.g., Salesforce AI Associate, Postman Expert, etc.).
  5. getGithubRepos: Performs an authenticated fetch to the GitHub API to return a live list of my active public repositories, showing updated dates, stars, and languages.
  6. askAboutBijon: A free-text search tool allowing natural language Q&A across the entire portfolio dataset (e.g., "What did he do at FAITE?" or "Summarize his research project at SLIIT").

🛠️ Tech Stack

  • Runtime: Node.js (v18+)
  • Language: TypeScript
  • Protocol: @modelcontextprotocol/sdk (Stdio transport)
  • JSON Data Layer: Custom file-based single source of truth for resume info.

📦 Getting Started

Prerequisites

  • Node.js installed (LTS recommended)
  • A GitHub Personal Access Token (GITHUB_TOKEN) with read-only public repository access (recommended to avoid API rate limits).

Setup

  1. Clone the repository:

    git clone https://github.com/Bijon2002/Build-Own-MCP.git
    cd Build-Own-MCP
    
  2. Install dependencies:

    npm install
    
  3. Configure Environment Variables: Create a .env file in the root directory (or copy from the template):

    GITHUB_TOKEN=your_github_personal_access_token_here
    
  4. Build the project:

    npm run build
    

🖥️ Local Integration (Claude Desktop)

To add this server to your local Claude Desktop client, edit the configuration file:

  1. Open your Claude Desktop config file:

    • On Windows: %APPDATA%\Claude\claude_desktop_config.json
    • On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  2. Add the following definition under the mcpServers property:

{
  "mcpServers": {
    "bijon-portfolio": {
      "command": "npx",
      "args": [
        "-y",
        "tsx",
        "A:/Build Own MCP/src/server.ts"
      ],
      "env": {
        "GITHUB_TOKEN": "your_github_token_here"
      }
    }
  }
}
  1. Restart Claude Desktop. You will now see the tool icon (🔌) with my portfolio tools active!

📂 Project Structure

├── data/
│   ├── portfolio-data.json   # Bio, education, experience, skills, socials
│   ├── projects.json         # Curated projects list
│   └── certificates.json     # Certifications list
├── src/
│   ├── lib/
│   │   ├── github.ts         # Live GitHub API query helper
│   │   └── loadData.ts       # JSON loader helper
│   ├── tools/
│   │   ├── askAboutBijon.ts  # Free-text Q&A tool
│   │   ├── getCertificates.ts
│   │   ├── getGithubRepos.ts
│   │   ├── getProfile.ts
│   │   ├── getProjects.ts
│   │   └── getSkills.ts
│   └── server.ts             # Entry point (MCP server & stdio setup)
├── tsconfig.json
├── package.json
└── README.md

👨‍💻 Author

Marislin Bijosilin (Bijon)

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选