MCP Deep Search
A server for performing deep web searches using the @just-every/search library, requiring API keys via an environment file.
MCP Deep Search
MCP server for deep web search using @just-every/search. Search across multiple providers including Google, Bing, Brave, DuckDuckGo, Perplexity, and more.
Quick Start
1. Create or use an environment file
Option A: Create a new .llm.env file in your home directory:
# Download example env file
curl -o ~/.llm.env https://raw.githubusercontent.com/just-every/mcp-deep-search/main/.env.example
# Edit with your API keys
nano ~/.llm.env
Option B: Use an existing .env file (must use absolute path):
# Example: /Users/yourname/projects/myproject/.env
# Example: /home/yourname/workspace/.env
2. Install
Claude Code
# Using ~/.llm.env
claude mcp add deep-search -s user -e ENV_FILE=$HOME/.llm.env -- npx -y @just-every/mcp-deep-search
# Using existing .env file (absolute path required)
claude mcp add deep-search -s user -e ENV_FILE=/absolute/path/to/your/.env -- npx -y @just-every/mcp-deep-search
# For debugging, check if ENV_FILE is being passed correctly:
claude mcp list
Other MCP Clients
Add to your MCP configuration:
{
"mcpServers": {
"deep-search": {
"command": "npx",
"args": ["-y", "@just-every/mcp-deep-search"],
"env": {
"ENV_FILE": "/path/to/.llm.env"
}
}
}
}
MCP Tools
deep_search
Perform web searches using a specific provider.
Parameters:
query(required): The search queryprovider: Search provider (default: brave)maxResults: Maximum results (default: 10)includeAnswer: Include AI answer if available (default: false)
comprehensive_research
Perform comprehensive research using AI agents that intelligently select and query multiple search engines.
Parameters:
query(required): The research topicmodelClass: AI model class (default: reasoning_mini)
Search Providers
| Provider | API Key Required | Description |
|---|---|---|
brave | BRAVE_API_KEY | Privacy-first search with structured results |
anthropic | ANTHROPIC_API_KEY | Deep multi-hop research |
openai | OPENAI_API_KEY | ChatGPT-grade contextual search |
google | GOOGLE_API_KEY | Gemini grounding search |
sonar / sonar-pro | OPENROUTER_API_KEY | Perplexity search variants |
xai | XAI_API_KEY | Real-time Grok search |
CLI Usage
# Basic search
mcp-deep-search search "your query"
# Search with specific provider
mcp-deep-search search "your query" -p brave
# Get more results
mcp-deep-search search "your query" -n 20
Troubleshooting
MCP Server Shows "Failed" in Claude
If you see "deep-search ✘ failed" in Claude, check these common issues:
-
Missing API Keys: The most common issue is missing API keys. Check that your ENV_FILE is properly configured:
# Test if ENV_FILE is working ENV_FILE=/path/to/your/.env npx @just-every/mcp-deep-search search "test" -
Incorrect Installation Command: Make sure you're using
-efor environment variables:# Correct - environment variable passed with -e flag before -- claude mcp add deep-search -s user -e ENV_FILE=$HOME/.llm.env -- npx -y @just-every/mcp-deep-search # Incorrect - trying to pass as argument claude mcp add deep-search -s user -- npx -y @just-every/mcp-deep-search --env ENV_FILE=$HOME/.llm.env -
Path Issues: ENV_FILE must use absolute paths:
# Good ENV_FILE=/Users/yourname/.llm.env ENV_FILE=$HOME/.llm.env # Bad ENV_FILE=.env ENV_FILE=~/.llm.env # ~ not expanded in some contexts -
Verify Installation: Check your MCP configuration:
claude mcp list -
Debug Mode: For detailed error messages, run manually:
ENV_FILE=/path/to/.env npx @just-every/mcp-deep-search
Getting API Keys
- Brave: brave.com/search/api
- Anthropic: console.anthropic.com
- OpenAI: platform.openai.com
- Google: makersuite.google.com
- OpenRouter: openrouter.ai
- xAI: x.ai
Auto-Restart Feature
The MCP server includes automatic restart capability by default for improved reliability:
- Automatically restarts the server if it crashes
- Handles unhandled exceptions and promise rejections
- Implements exponential backoff (max 10 attempts in 1 minute)
- Logs all restart attempts for monitoring
- Gracefully handles shutdown signals (SIGINT, SIGTERM)
For development/debugging without auto-restart:
# Run directly without restart wrapper
npm run serve:dev
License
MIT © Just Every
Related Servers
Supavec
Fetch relevant embeddings and content from Supavec for AI assistants.
Google Search
Web search and webpage content extraction using the Google Custom Search API.
12306-mcp
Search for train tickets on 12306, the official China Railway website.
Scientific Paper Harvester
Harvests scientific papers from arXiv and OpenAlex, providing real-time access to metadata and full text.
AnySearch
Unified real-time search engine skill for AI agents.
Sketchfab
Search, view details, and download 3D models from the Sketchfab platform.
Campertunity
Search campgrounds around the world on campertunity, check availability, and provide booking links.
Airbnb
Search for Airbnb listings and get detailed information about accommodations.
RedNote MCP
Search and retrieve content from the Xiaohongshu (Red Book) platform.
Mamont Search
A search engine server that provides tools for search queries and cache retrieval.