researchmcp
Multi-Search API Aggregator Server built with Deno + Hono
Documentation
ResearchMCP
A research tool that combines the Model Context Protocol (MCP) with Brave Search, Tavily Search,
etc. to achieve research capabilities equivalent to (or aiming to be equivalent to) ChatGPT's
DeepResearch.
Technology Stack
- Runtime: Deno
- Framework: Hono
- Error Handling: Neverthrow (Result pattern)
- Deployment: Docker container
Setup
Local Development
1. Install Deno
2. Clone the repository
3. Set environment variables
4. Run the application:
make dev # HTTP server
make mcp # MCP server for Claude DesktopContainer Environment
1. Install Docker and Docker Compose
2. Set environment variables in a `.env` file
3. Build and run the container:
make d-build
make d-upDevelopment Commands
# Local development
make dev # Start HTTP server with watch mode
make mcp # Start MCP server for Claude Desktop
make test # Run tests
make lint # Run linter
make format # Format code
make check # Type check
# Docker development
make d-build # Build the image
make d-dev # Start container with live reload
make d-up # Run in background
make d-logs # View logs
make d-down # Stop containerMCP Integration with Claude Desktop
1. Run the MCP server: `make mcp`
2. In Claude Desktop, add a new MCP server with the following configuration:
{
"mcpServers": {
"MCPSearch": {
"description": "Web search powered by Brave, Tavily, etc.",
"command": "/absolute/path/to/ResearchMCP/cli.ts",
"args": [],
"transport": "stdio",
"env": {
"BRAVE_API_KEY": "your_brave_api_key_here",
"TAVILY_API_KEY": "your_tavily_api_key_here"
}
}
}
}Replace `/absolute/path/to/ResearchMCP/cli.ts` with the actual path to the cli.ts file.
Known Limitations
- Language Support: Brave Search API has limited support for non-Latin characters. Searches in
Japanese, Chinese, Korean, and other non-Latin script languages may fail with encoding errors. For
best results, use English queries.
Features
- Web Search: Search the web using Brave Search API through Claude Desktop
- MCP Protocol: Full compliance with the Model Context Protocol
- Caching: Search results are cached to improve performance and reduce API calls
Frequently asked questions
What is researchmcp?
researchmcp is Multi-Search API Aggregator Server built with Deno + Hono
How do I install researchmcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is researchmcp open source?
Yes — it is hosted on GitHub at https://github.com/riii111/ResearchMCP and has 7 stars.
Related MCP tools
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Ag...
The official TypeScript SDK for Model Context Protocol servers and clients Trusted by 10500+ developers. Trusted by 10500+ developers.
Visual testing tool for MCP servers TypeScript-based implementation. Trusted by 7300+ developers. Trusted by 7300+ developers.
It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic TypeScript-based implementation.
🤖 A visualization mcp contains 25+ visual charts using @antvis. Using for chart generation and data analysis. TypeScript-based implementation.
Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices) TypeScript-based implementation.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP