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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.