MCP Nexus
mcp-nexus is a Multi-Provider Model Context Protocol (MCP) server that integrates the Tavily and Brave Search search APIs, providing a unified tool interface, API key rotation management, a Web management interface, and usage monitoring functions.
rating : 2.5 points
downloads : 5.0K
What is mcp-nexus?
mcp-nexus is an intelligent search aggregation server that integrates the two major search services of Tavily and Brave Search. It provides web search capabilities for AI assistants and applications through a unified interface. It solves the rate limit problem of a single API key, supports multi-key rotation, and offers a user-friendly management interface.How to use mcp-nexus?
Using mcp-nexus is very simple: 1) Deploy the server (supports Docker, local Node.js, or Cloudflare Workers), 2) Add API keys and create client tokens through the management interface, 3) Configure the MCP client connection in your AI assistant or application. The whole process does not require writing complex code.Use cases
mcp-nexus is very suitable for AI application scenarios that require stable and reliable web search capabilities: AI research assistants, content creation tools, data analysis platforms, news aggregators, academic research tools, etc. It is especially suitable for production environments that need to handle a large number of search requests or require high availability.Main features
Unified search API
Supports both Tavily and Brave Search search services through a single MCP endpoint, providing a consistent interface experience.
Multi-key management
Supports adding and managing multiple API keys, and automatically rotates them to distribute the load and handle rate limits.
Web management interface
Provides an intuitive Web interface for easily managing API keys, client tokens, viewing usage statistics, and configuring server settings.
Usage monitoring
Tracks tool usage in real-time, views query history, and understands the most commonly used tools and query patterns.
Flexible search strategy
Supports multiple search modes: Tavily only, Brave only, parallel queries, or Brave first with Tavily as a backup. It can be dynamically configured without restarting the server.
Intelligent rate limiting
Built-in rate limits for clients and upstream APIs prevent abuse and effectively manage API costs.
Multiple deployment methods
Supports local Node.js operation, Docker containerized deployment, and Cloudflare Workers serverless deployment.
Client authentication
Secures the MCP endpoint through Bearer tokens. Tokens can be easily created and revoked through the management interface.
Advantages
High availability: Multi-key rotation ensures continuous service availability
Cost optimization: Intelligently selects the most cost-effective search provider
Easy to manage: An intuitive Web interface reduces the complexity of operation and maintenance
Flexible configuration: Supports multiple search strategies and deployment methods
Strong security: Client authentication and key encryption protection
Comprehensive monitoring: Detailed usage statistics and query logs
Limitations
Initial configuration requires obtaining Tavily and/or Brave API keys
Parallel search mode consumes the quotas of both providers simultaneously
Basic server operation and maintenance knowledge is required for deployment
Advanced features may require an understanding of the MCP protocol concept
How to use
Environment preparation
Copy the environment variable configuration file and set the necessary parameters, such as the administrator token and database connection.
Start the server
Use Docker Compose to quickly start the server (recommended) or run it locally using Node.js.
Access the management interface
Open a browser to access the management interface (default http://localhost:8787/admin) and log in with the administrator token.
Add API keys
Add your Tavily and Brave Search API keys on the Keys page of the management interface.
Create client tokens
Create tokens for MCP client connections on the Tokens page.
Configure the MCP client
Configure the MCP client in your AI assistant or application and use the created client token for connection.
Usage examples
Academic research assistant
Researchers use mcp-nexus to provide the latest academic materials and web information search capabilities for AI research assistants.
Content creation tool
Content creators use mcp-nexus to obtain the latest industry trends and fact-checking information to ensure content accuracy and timeliness.
Technical document update
The technical documentation team uses mcp-nexus to automatically check API changes and obtain the latest technical specification information.
Market analysis report
Market analysts use mcp-nexus to collect competitor information and industry trend data.
Frequently Asked Questions
How many API keys does mcp-nexus require?
How to obtain API keys for Tavily and Brave Search?
What deployment methods does mcp-nexus support?
What are the advantages and disadvantages of the parallel search mode?
How to monitor API usage and remaining quotas?
What is the difference between client tokens and administrator tokens?
What MCP clients does mcp-nexus support?
Where is the data stored? How to back it up?
Related resources
GitHub repository
The complete source code and latest updates of mcp-nexus
Model Context Protocol official website
The official documentation and specifications of the MCP protocol
Tavily API documentation
Detailed usage instructions for the Tavily search API
Brave Search API documentation
Registration and usage guidelines for the Brave Search API
Cloudflare Workers deployment guide
Detailed instructions for one-click deployment to Cloudflare Workers
Docker official documentation
Installation and usage tutorials for Docker and Docker Compose

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
21.5K
4.5 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
34.5K
5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.7K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.5K
4.3 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
64.6K
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.3K
5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
49.3K
4.8 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.1K
4.5 points






