Nexus MCP Server
Enables hybrid web search and intelligent content extraction, combining semantic search with documentation-optimized reading that strips noise and returns clean, token-efficient context for AI agents.
README
๐ Nexus MCP Server
The Hybrid Search & Retrieval Engine for AI Agents.
Nexus is a local Model Context Protocol (MCP) server that combines the best features of Exa (semantic web search) and Ref (documentation-optimized reading). It provides your AI agent (Claude, Cursor, etc.) with the ability to search the web and extract surgical, token-efficient context from documentation without requiring external API keys.
โจ Features
1. Hybrid Search (nexus_search)
Nexus understands that searching for news is different from searching for API docs.
- General Mode: Performs broad web searches (like Exa) to find articles, news, and general information.
- Docs Mode: Automatically filters results to prioritize technical domains (
readthedocs,github,stackoverflow, official documentation).
2. Intelligent Reading (nexus_read)
Nexus doesn't just dump HTML into your context window. It parses content based on intent.
- General Focus: Cleans articles, removing ads, navigation bars, and fluff. Perfect for reading news or blog posts.
- Code Focus: Aggressively strips conversational text, retaining only Headers, Code Blocks, and Tables. This mimics
ref.tools, ensuring your model gets pure syntax without the noise. - Auto-Detect: Automatically switches to "Code Focus" when visiting technical sites like GitHub or API references.
3. Privacy & Cost
- No API Keys Required: Uses DuckDuckGo for search and standard HTTP requests for retrieval.
- Runs Locally: Your data stays on your machine until the cleaned context is sent to the LLM.
๐ ๏ธ Installation
Prerequisites
- Python 3.10+
uv(Recommended) orpip
Quick Install (Recommended)
Install directly from GitHub - no cloning needed:
# Using uvx (no installation, runs on-demand)
uvx --from git+https://github.com/rcdelacruz/nexus-mcp.git nexus-mcp
# Or install with pip
pip install git+https://github.com/rcdelacruz/nexus-mcp.git
Development Install
For local development or contributing:
- Clone the repository:
git clone https://github.com/rcdelacruz/nexus-mcp.git
cd nexus-mcp
- Install in development mode:
# Create virtual environment
python3 -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install the package in editable mode
pip install -e .
- For development with testing tools:
pip install -e ".[dev]"
โ๏ธ Configuration
Claude Code (CLI)
Quick Setup (Recommended - Install from GitHub):
# Add the server globally (available in all projects)
claude mcp add nexus --scope user -- \
uvx --from git+https://github.com/rcdelacruz/nexus-mcp.git nexus-mcp
# Verify installation
claude mcp list # Should show: โ Connected
Alternative: Local Development Setup
If you cloned the repository for development:
# Navigate to nexus-mcp directory
cd /path/to/nexus-mcp
# Install dependencies first
python3 -m venv .venv
source .venv/bin/activate
pip install -e .
# Add the server to Claude Code (project scope)
claude mcp add nexus --scope project -- \
$(pwd)/.venv/bin/python $(pwd)/nexus_server.py
# Verify installation
claude mcp list
Configuration Scopes:
--scope user- Available across all projects (recommended for GitHub install)--scope project- Creates.mcp.json(shareable via git)--scope local- Personal config in~/.claude.json
Check server status:
claude mcp list # Should show: nexus - โ Connected
/mcp # In conversation: shows available tools
Claude Desktop / Cursor
Config Location:
- MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Recommended: Install from GitHub with uvx
{
"mcpServers": {
"nexus": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/rcdelacruz/nexus-mcp.git",
"nexus-mcp"
]
}
}
}
Alternative: Using local installation
After running pip install git+https://github.com/rcdelacruz/nexus-mcp.git:
{
"mcpServers": {
"nexus": {
"command": "nexus-mcp"
}
}
}
For local development:
If you cloned the repo and installed with pip install -e .:
{
"mcpServers": {
"nexus": {
"command": "/ABSOLUTE/PATH/TO/.venv/bin/python",
"args": ["/ABSOLUTE/PATH/TO/nexus_server.py"]
}
}
}
Replace /ABSOLUTE/PATH/TO/ with the actual path to your clone.
๐ Usage
Once connected, simply prompt Claude naturally. Nexus handles the tool selection.
Verify It's Working
Check server connection:
claude mcp list
# Should show: nexus - โ Connected
# In a Claude Code conversation:
/mcp
# Should show nexus with 2 tools available
See VERIFICATION.md for detailed testing instructions.
Scenario 1: Technical Research (Ref Emulation)
User: "How do I use
asyncio.gatherin Python? Check the docs."
- Nexus Action:
- Search:
nexus_search(query="python asyncio gather", mode="docs") - Read:
nexus_read(url="docs.python.org/...", focus="code")
- Search:
- Result: The AI receives only the function signature and code examples, saving context window space.
Scenario 2: General Research (Exa Emulation)
User: "Search for the latest updates on the NVIDIA Blackwell chip."
- Nexus Action:
- Search:
nexus_search(query="NVIDIA Blackwell updates", mode="general") - Read:
nexus_read(url="techcrunch.com/...", focus="general")
- Search:
- Result: The AI reads a clean, ad-free summary of the news article.
๐ง Architecture
Nexus is built on the Model Context Protocol using the FastMCP Python SDK.
| Component | Technology | Purpose |
|---|---|---|
| MCP Framework | FastMCP |
Server implementation and tool registration |
| Search Backend | DDGS (DuckDuckGo) |
Free web search without API keys |
| HTTP Client | httpx |
Async HTTP requests with timeout handling |
| HTML Parsing | BeautifulSoup4 |
Intelligent content extraction |
| Doc Detection | Heuristic URL matching | Auto-detection of technical sites |
Production Features
โ Comprehensive Error Handling - All edge cases covered with graceful fallbacks
โ Input Validation - URL format, parameter bounds, and mode validation
โ Proper Logging - Structured logging instead of print statements
โ Configurable Limits - Timeouts, content length, and result counts
โ 85% Test Coverage - 19 comprehensive unit tests
โ Type Hints - Full type annotations for better IDE support
โ Dependency Management - Modern pyproject.toml configuration
๐งช Testing
Run the test suite:
# Activate virtual environment
source .venv/bin/activate
# Run all tests with coverage
pytest
# Run specific test file
pytest tests/test_nexus_server.py -v
# Run manual integration test
python test_manual.py
๐ Project Structure
nexus-mcp/
โโโ nexus_server.py # Main MCP server implementation
โโโ tests/ # Comprehensive test suite
โ โโโ __init__.py
โ โโโ test_nexus_server.py
โโโ test_manual.py # Manual integration testing
โโโ pyproject.toml # Project configuration & dependencies
โโโ LICENSE # MIT License
โโโ README.md # This file
โโโ .gitignore # Git ignore rules
๐ค Contributing
Contributions are welcome! Please ensure:
- All tests pass (
pytest) - Code coverage remains above 80%
- Follow existing code style and patterns
- Add tests for new features
๐ License
MIT License - See LICENSE file for details. Free to use and modify.
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.