This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
An MCP server that gives Claude Code web search and product research capabilities. Never leave your terminal to research a product again.
5 tools, one server:
Tool | What It Does |
| Full product brief — features, pricing, tech, API |
| Side-by-side comparison of 2-5 products |
| Focused pricing/plans lookup |
| Find competitors and alternatives |
| Raw web search for anything else |
Related MCP server: Specialized AI Search Tools
cd product-researcher-mcp
pip install -r requirements.txtProvider | Free Tier | Best For | Sign Up |
Tavily | 1,000/month | AI agents (returns summaries) | |
Brave | 2,000/month | Privacy, good free tier | |
Serper | 2,500 total | Google-quality results |
cp .env.example .env
# Edit .env — set SEARCH_PROVIDER and the matching API keyAdd this to your Claude Code MCP config (~/.claude/claude_desktop_config.json or project-level .mcp.json):
{
"mcpServers": {
"product-researcher": {
"command": "python",
"args": ["/full/path/to/product-researcher-mcp/server.py"],
"env": {
"SEARCH_PROVIDER": "tavily",
"TAVILY_API_KEY": "tvly-your-key-here"
}
}
}
}Or if using Brave:
{
"mcpServers": {
"product-researcher": {
"command": "python",
"args": ["/full/path/to/product-researcher-mcp/server.py"],
"env": {
"SEARCH_PROVIDER": "brave",
"BRAVE_API_KEY": "BSA-your-key-here"
}
}
}
}In Claude Code, just ask:
research Kling AIcompare Supabase vs Firebase vs PlanetScalewhat's the pricing for Vercelfind alternatives to Midjourney for AI image generationYou ask Claude Code
→ Claude calls research_product tool
→ MCP server builds smart search queries
→ Hits your search API (Tavily/Brave/Serper)
→ Deduplicates & formats results
→ Returns structured markdown brief
→ Claude synthesizes the answer for youThe server is search-API-agnostic. Swap providers any time by changing one env var.
product-researcher-mcp/
├── server.py # The MCP server (all tools + search adapters)
├── requirements.txt # Python dependencies
├── .env.example # Config template
└── README.md # You're hereWant to add a new search provider? Add a function following the pattern:
async def _search_newprovider(query: str, max_results: int) -> List[Dict[str, Any]]:
# Hit the API, return list of {"title": ..., "content": ..., "url": ...}
passThen add it to the providers dict in the search() function. Done.
MIT
Built by Quantaus
Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.
8-tool AI web intelligence suite: search, scrape, screenshot, SEO, docs, crypto, code.
Search and look up products across thousands of online stores, normalized into one schema.
Search and look up products across thousands of online stores, normalized into one schema.
