Exa Search
Semantic Search Search & ProductivityInstall Command
npx clawhub@latest install exa
Installation Guide
Make sure Node.js 22+ and OpenClaw are installed. Run openclaw --version in your terminal to verify.
Run the install command above in your terminal. ClawHub will automatically download and install Exa Search to the ~/.openclaw/skills/ directory.
Run openclaw skills list to check your installed skills and confirm Exa Search appears in the list.
Follow the configuration instructions in the description below to add skill settings to ~/.config/openclaw/openclaw.json5.
~/.openclaw/skills/ or the skills/ directory in your project root. Make sure the folder contains a SKILL.md file.
Detailed Description
Exa is a next-generation search engine based on neural networks. Unlike traditional keyword matching, Exa uses semantic embeddings to understand query meaning and find truly relevant content, particularly excelling at discovering high-quality pages that traditional search engines struggle to find.
Core Features
- Semantic Search (search): Describe what you're looking for in natural language, and Exa uses Embedding models to understand semantics and return the most relevant results, rather than simple keyword matching
- Similar Search (find_similar): Input a URL to find other pages with similar content or topics, ideal for discovering related resources
- Content Extraction (get_contents): Get the full content of search result pages, with support for returning clean text or highlighted key snippets
- Advanced Filtering: Supports filtering results by domain, publication date, and content type (articles/papers/tweets, etc.)
Configuration
{
"mcpServers": {
"exa": {
"command": "npx",
"args": ["-y", "exa-mcp-server"],
"env": {
"EXA_API_KEY": "your-exa-api-key" // Get from exa.ai
}
}
}
}
Use Cases
- Technical research: Describe requirements in natural language to find the most relevant open-source projects and technical articles
- Competitor discovery: Input a product URL to find all similar products and alternatives
- Academic research: Semantically search for related papers and research findings
- Content recommendations: Discover similar content based on articles the user has read