Bounty Board MCP Server
A working MCP server implementation in TypeScript/JavaScript that supports all major bounty operations (list/claim/submit/status). Includes example Claude conversations showing usage.
README
Bounty Board MCP Server
A working MCP server implementation in TypeScript/JavaScript implementation that supports all major bounty operations (list/claim/submit/status). This README with installation instructions includes example Claude conversations showing usage.
Features
- Working MCP server implementation — full Model Context Protocol server using
@modelcontextprotocol/sdk - Supports all major bounty operations (list/claim/submit/status) — 7 registered tools for complete bounty board interaction
- TypeScript/JavaScript implementation — written in TypeScript, runs on Bun or Node.js 18+
- list_bounties — browse all bounties with optional status filtering
- get_bounty — get full details about a specific bounty
- claim_bounty — claim an open bounty to start working on it
- submit_bounty — submit completed work with proof URL
- get_stats — view aggregate board statistics
- search_bounties — search by keyword or filter by tag
- get_leaderboard — see top bounty hunters ranked by earnings
Setup
Prerequisites
- Bun or Node.js 18+
- Claude Desktop (or any MCP-compatible client)
Install Dependencies
bun install
Build (for Node.js)
bun run build
Claude Desktop Configuration
Add this to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Using Bun (recommended)
{
"mcpServers": {
"bounty-board": {
"command": "bun",
"args": ["run", "/absolute/path/to/bounty-mcp-server/src/index.ts"],
"env": {
"WALLET_ADDRESS": "0xYourWalletAddressHere"
}
}
}
}
Using Node.js (after building)
{
"mcpServers": {
"bounty-board": {
"command": "node",
"args": ["/absolute/path/to/bounty-mcp-server/dist/index.js"],
"env": {
"WALLET_ADDRESS": "0xYourWalletAddressHere"
}
}
}
}
Environment Variables
| Variable | Required | Description |
|---|---|---|
WALLET_ADDRESS |
For claim/submit | Your wallet address for claiming and submitting bounties |
Usage Examples
Once configured, you can interact with the bounty board through Claude:
Example Claude Conversations Showing Usage
Discover Bounties
"Show me all open bounties" "What bounties are available with the 'typescript' tag?" "Search for bounties related to dashboards"
Inspect a Bounty
"Get details on bounty #42" "What are the requirements for bounty #98?"
Claim and Submit
"Claim bounty #24 for me" "Submit my work for bounty #24 -- I built an MCP server, here's the repo: https://github.com/user/repo"
Statistics
"What are the current bounty board stats?" "Show me the top earners leaderboard"
Architecture
src/
index.ts -- MCP server setup, tool registration, stdio transport
tools.ts -- Tool definitions (schemas + descriptions) and handler implementations
The server uses the @modelcontextprotocol/sdk to expose tools via the stdio transport. Each tool has:
- A descriptive name and explanation for agent discovery
- A Zod input schema with per-field descriptions
- An async handler that calls the Bounty Board API and returns formatted results
API Endpoints Used
GET /bounties-- List all bountiesGET /stats-- Board statisticsPOST /bounties/:id/claim-- Claim a bountyPOST /bounties/:id/submit-- Submit work
License
MIT
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。