TrySellr MCP Server
AI-powered selling intelligence for multiple online marketplaces, enabling item analysis, optimized listings, pricing checks, negotiation coaching, and batch operations via any MCP-compatible AI assistant.
README
TrySellr MCP Server
AI-powered selling intelligence for Facebook Marketplace, eBay, Mercari, OfferUp, and Craigslist.
TrySellr plugs into any MCP-compatible AI assistant (Claude, ChatGPT, Cursor, etc.) and gives sellers superpowers: instant item analysis, conversion-optimized listings, cross-platform pricing data, negotiation coaching, demand intelligence, and batch processing.
One server. Every AI assistant. Every marketplace.
Tools
| Tool | What It Does | Tier |
|---|---|---|
analyze_item |
Identify items, estimate value, detect brand/model | Free (3/day) |
optimize_listing |
Generate high-converting listings with SEO | Free (3/day) |
price_check |
Cross-platform pricing with sell-speed estimates | Pro |
negotiate_assist |
AI negotiation coach with copy-paste replies | Pro |
demand_radar |
Trending items and demand signals by location | Pro |
performance_track |
Listing health score and optimization plan | Pro |
batch_list |
Process 2-25 items at once | Power |
cross_list |
Generate listings for 2-6 platforms simultaneously | Power |
Pricing
- Free: 3 analyze + 3 optimize calls/day. No credit card.
- Pro ($19/mo): All analysis, pricing, negotiation, and tracking tools.
- Power Seller ($49/mo): Everything + batch processing + cross-listing.
Quick Start
1. Get Your API Key
curl -X POST https://trysellr.com/api/signup \
-H "Content-Type: application/json" \
-d '{"email": "you@example.com"}'
2. Connect to Claude Desktop
Add to your Claude Desktop MCP config (claude_desktop_config.json):
{
"mcpServers": {
"trysellr": {
"url": "https://trysellr.com/mcp",
"headers": {
"x-trysellr-key": "tsk_your_api_key_here"
}
}
}
}
3. Start Selling Smarter
Open Claude and say:
- "Analyze this item: Sony WH-1000XM4 headphones, used, good condition, comes with case"
- "Write a Facebook Marketplace listing for a mid-century modern coffee table, walnut, 48x24, great condition"
- "What's trending in Electronics in Nashville right now?"
API Endpoint
Base URL: https://trysellr.com/mcp
Transport: Streamable HTTP (MCP spec 2025-03-26)
Auth: Header x-trysellr-key: tsk_your_key
MCP Protocol
# Initialize
curl -X POST https://trysellr.com/mcp \
-H "Content-Type: application/json" \
-H "x-trysellr-key: tsk_your_key" \
-d '{"jsonrpc":"2.0","method":"initialize","params":{},"id":1}'
# List tools
curl -X POST https://trysellr.com/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/list","params":{},"id":2}'
# Call a tool
curl -X POST https://trysellr.com/mcp \
-H "Content-Type: application/json" \
-H "x-trysellr-key: tsk_your_key" \
-d '{
"jsonrpc":"2.0",
"method":"tools/call",
"params":{
"name":"analyze_item",
"arguments":{"description":"iPhone 14 Pro Max 256GB space black, good condition, no cracks"}
},
"id":3
}'
Development
# Install
npm install
# Run locally
cp .env.example .env # Edit with your keys
npm run dev
# Build
npm run build
# Test
npm test
Deploy
Railway (Recommended)
railway login
railway init
railway up
Docker
docker build -t trysellr-mcp .
docker run -p 8080:8080 --env-file .env trysellr-mcp
Fly.io
fly launch
fly deploy
Architecture
┌─────────────────────────────────────────────┐
│ AI Assistants (Clients) │
│ Claude │ ChatGPT │ Cursor │ Any MCP Client │
└────────────────┬────────────────────────────┘
│ MCP Protocol (JSON-RPC 2.0)
│ POST /mcp
┌────────────────▼────────────────────────────┐
│ TrySellr MCP Server │
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │
│ │ Auth │ │ Rate │ │ Usage │ │
│ │ Layer │ │ Limiter │ │ Tracker │ │
│ └────┬─────┘ └────┬─────┘ └────┬─────┘ │
│ └─────────┬───┘────────────┘ │
│ ┌──────────────▼──────────────────────┐ │
│ │ Tool Registry (8 tools) │ │
│ │ analyze │ optimize │ price │ batch │ │
│ │ negotiate │ demand │ cross │ track │ │
│ └──────────────┬──────────────────────┘ │
│ ┌──────────────▼──────────────────────┐ │
│ │ Service Layer │ │
│ │ AI Engine │ Pricing │ Database │ │
│ └─────────────────────────────────────┘ │
└─────────────────────────────────────────────┘
License
MIT — Built by BOEZAC / TrySellr
https://trysellr.com
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。