UpworkBridge

UpworkBridge

A Model Context Protocol (MCP) server that connects AI coding assistants and agentic workflows to the Upwork freelance marketplace. Enables AI-powered job discovery, proposal generation, and contract management through a structured tool interface.

Category
访问服务器

README

UpworkBridge — MCP Server for Upwork

A Model Context Protocol (MCP) server that connects AI coding assistants and agentic workflows to the Upwork freelance marketplace. Enables AI-powered job discovery, proposal generation, and contract management through a structured tool interface.

Overview

UpworkBridge exposes Upwork's platform capabilities as MCP tools, allowing AI agents to:

  • Search jobs across 25+ skill categories with configurable scoring and filtering
  • Generate tailored proposals using freelancer profile data and job-specific context
  • Manage contracts and messages (proposed — requires OAuth scope)
  • Monitor activity via a cron-enabled scanning pipeline

Architecture

┌─────────────────────────────────────────────────────┐
│                  AI Assistant (Host)                  │
│  (Claude Code, Cursor, Copilot, Hermes Agent, etc.) │
└────────────────────┬────────────────────────────────┘
                     │ MCP Protocol (stdio/SSE)
                     ▼
┌─────────────────────────────────────────────────────┐
│                  UpworkBridge Server                  │
│                                                       │
│  ┌──────────────┐    ┌───────────────────────────┐   │
│  │  Scanner     │ →  │  Job Search & Scoring     │   │
│  │  Module      │    │  - 25+ predefined queries │   │
│  └──────────────┘    │  - Multi-tier categories  │   │
│                      │  - Smart scoring engine   │   │
│  ┌──────────────┐    └───────────────────────────┘   │
│  │  Proposer    │    ┌───────────────────────────┐   │
│  │  Module      │ →  │  Proposal Generation      │   │
│  └──────────────┘    │  - AI-assisted drafting   │   │
│                      │  - Skill-based templates  │   │
│                      │  - Best practices engine  │   │
│  ┌──────────────┐    └───────────────────────────┘   │
│  │  OAuth       │    ┌───────────────────────────┐   │
│  │  Handler     │ →  │  Token Management         │   │
│  └──────────────┘    │  - OAuth 2.0 auth flow    │   │
│                      │  - Auto token refresh     │   │
│  ┌──────────────┐    └───────────────────────────┘   │
│  │  Config      │    ┌───────────────────────────┐   │
│  │  Engine      │ →  │  Search params, scoring   │   │
│  └──────────────┘    │  weights, user profile    │   │
│                      └───────────────────────────┘   │
└────────────────────┬────────────────────────────────┘
                     │ Upwork API (OAuth 2.0)
                     ▼
┌─────────────────────────────────────────────────────┐
│                  Upwork Platform                      │
│  Job listings · Proposals · Contracts · Messages     │
└─────────────────────────────────────────────────────┘

Quick Start

Prerequisites

  • Python 3.10+
  • Upwork API credentials (OAuth 2.0 — apply here)

Installation

# Clone the repo
git clone https://github.com/your-org/upworkbridge.git
cd upworkbridge

# Install dependencies
pip install -r requirements.txt

# Configure credentials
cp config.example.py config.py
# Edit config.py with your Upwork Client ID and Secret

# Run initial OAuth authorization
python src/scanner.py --auth

# Search for jobs
python src/scanner.py

# Generate a proposal
python src/propose.py --job-id <JOB_ID>

MCP Integration

To connect UpworkBridge to an MCP-compatible AI assistant:

{
  "mcpServers": {
    "upwork": {
      "command": "python",
      "args": ["/path/to/upworkbridge/src/scanner.py", "--mcp"],
      "env": {
        "UPWORK_CLIENT_ID": "your_client_id",
        "UPWORK_CLIENT_SECRET": "your_client_secret"
      }
    }
  }
}

Features

🔍 Job Scanner

Searches Upwork across 10 categories organized in 3 tiers:

Tier Category Target Rate Query Volume
1 AI/ML Implementation $85–$175/hr 5 queries
1 Government/Defense IT $100–$250/hr 2 queries
2 Data Analysis $40–$80/hr 3 queries
2 Process Automation $50–$100/hr 3 queries
2 Technical Writing $40–$80/hr 2 queries
3 Language Services $35–$55/hr 2 queries
3 Systems Admin $35–$65/hr 2 queries
3 Virtual Assistant $20–$45/hr 1 query
3 Real Estate $30–$60/hr 1 query
3 AI Training $40–$80/hr 1 query

📊 Smart Scoring

Jobs are scored 0–100 based on:

Factor Weight Description
Payment Verified 25 pts Client must have verified payment
Client Rating 10× Multiplied by (rating - 3) / 2
Budget 5–30 pts Scaled by project value
Region 10 pts US/CA/UK/AU preference
Freshness 15 pts Posted within 24 hours
Competition 5–10 pts Fewer proposals = higher score

📝 Proposal Generator

AI-assisted proposal drafting with:

  • Job-specific context analysis
  • Freelancer profile integration
  • Skill-based template matching
  • Best-practices checklist
  • Dry-run mode for review before submission

Configuration

All configuration lives in config.py:

  • API Credentials — OAuth 2.0 client ID and secret
  • Search Queries — Customizable per category
  • Scoring Weights — Adjustable preference factors
  • Filtering Rules — Minimum client rating, budget thresholds, country preferences
  • Freelancer Profile — Skills, certifications, portfolio, rate range

Roadmap

  • [x] Job scanning with multi-query search
  • [x] AI-assisted proposal generation
  • [x] OAuth 2.0 token management
  • [ ] MCP server mode (stdio transport)
  • [ ] Proposal submission & tracking
  • [ ] Message monitoring
  • [ ] Contract status tracking
  • [ ] Docker deployment
  • [ ] Pre-built GitHub Action for cron scanning

License

MIT — see LICENSE.

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