Nexus Documentation

Nexus is an AI Router that provides a unified endpoint for all your MCP (Model Context Protocol) servers, APIs, and LLM providers. It enables you to aggregate, govern, and manage your entire AI infrastructure through a single interface.

Nexus acts as a unified gateway between AI assistants and multiple Model Context Protocol (MCP) servers. Instead of configuring each MCP server individually in every AI tool, Nexus provides:

• Single endpoint for all your MCP tools
• Unified authentication with OAuth2 token forwarding
• Performance optimization through intelligent connection caching
• Tool aggregation with automatic namespacing to prevent conflicts
• Enterprise-ready security with TLS and authentication options

Get Nexus working with your AI assistant in minutes:

# Using the install script
curl -fsSL https://nexusrouter.com/install | bash

# Or run it with Docker
docker run -p 8000:8000 \
  -v $(pwd)/nexus.toml:/etc/nexus.toml \
  ghcr.io/grafbase/nexus:latest

Create a nexus.toml file:

# Basic MCP configuration
[mcp]
enabled = true
path = "/mcp"

# Add a simple file system server
[mcp.servers.filesystem]
cmd = ["npx", "-y", "@modelcontextprotocol/server-filesystem", "/home/user/documents"]

# Add a GitHub MCP server
[mcp.servers.github]
url = "https://api.github.com/mcp"

[mcp.servers.github.auth]
token = "{{ env.GITHUB_TOKEN }}"

# Start with default settings
nexus

# Or specify a config file
nexus --config ./nexus.toml

1. Open Cursor Settings (Cmd+, on macOS)
2. Search for "Model Context Protocol"
3. Enable MCP support
4. Add to the MCP server configuration:

{
  "nexus": {
    "transport": {
      "type": "http",
      "url": "http://localhost:8000/mcp"
    }
  }
}

Nexus simplifies MCP integration by exposing just two tools to AI assistants:

1. search - Discover tools from all connected MCP servers
2. execute - Run any discovered tool

This design allows Nexus to aggregate tools from multiple servers without overwhelming the AI assistant with hundreds of individual tools.

• Support for STDIO (subprocess), SSE, and HTTP MCP servers
• Automatic protocol detection for remote servers
• Environment variable substitution in configuration

• Natural language tool discovery across all connected servers
• Fuzzy matching for finding relevant tools quickly
• Namespaced tools prevent conflicts between servers
• Avoid context bloating

• OAuth2 authentication with JWT validation
• Token forwarding to downstream servers
• TLS configuration for secure connections
• CORS and CSRF protection

• Single binary installation
• Docker support with minimal configuration
• Health checks and monitoring endpoints

claude mcp add --transport http nexus http://localhost:8000/mcp

Once connected, your AI assistant will see two tools:

• Use search to find available tools: search for "file read"
• Use execute to run them: execute filesystem__read_file with path "/home/user/documents/readme.md"

• Installation - Install Nexus using various methods
• Server Configuration - Configure the Nexus server and security settings
• MCP Configuration - Set up and manage MCP servers

• Consolidate multiple development tools into one interface
• Switch between local and remote MCP servers seamlessly
• Test and debug MCP server implementations

• Share a common set of tools across the organization
• Control access to sensitive tools with authentication
• Monitor tool usage and performance

• Implement governance and compliance for AI tool usage
• Secure sensitive operations with OAuth2 and token forwarding
• Scale MCP server deployments with load balancing

• GitHub Issues: github.com/grafbase/nexus/issues
• Discord Community: Join our Discord
• Documentation: You're already here!