What is exa-web-search-free?

It is Exa's free AI-powered search suite that provides web, code, and company research capabilities without an API key.

What search types are supported?

Web (default), code (GitHub/Stack Overflow), and company (business intel). You can specify search_type or rely on defaults.

Do I need an API key?

No API key is required; setup is done via mcporter to connect to the Exa MCP endpoint.

exa-web-search-free

npx machina-cli add skill PHY041/claude-agent-skills/exa-web-search-free --openclaw

Files (1)

SKILL.md

2.7 KB

Exa Web Search (Free)

Neural search for web, code, and company research. No API key required.

Setup

Verify mcporter is configured:

mcporter list exa

If not listed:

mcporter config add exa https://mcp.exa.ai/mcp

Core Tools

web_search_exa

Search web for current info, news, or facts.

mcporter call 'exa.web_search_exa(query: "latest AI news 2026", numResults: 5)'

Parameters:

query - Search query
numResults (optional, default: 8)
type (optional) - "auto", "fast", or "deep"

get_code_context_exa

Find code examples and docs from GitHub, Stack Overflow.

mcporter call 'exa.get_code_context_exa(query: "React hooks examples", tokensNum: 3000)'

Parameters:

query - Code/API search query
tokensNum (optional, default: 5000) - Range: 1000-50000

company_research_exa

Research companies for business info and news.

mcporter call 'exa.company_research_exa(companyName: "Anthropic", numResults: 3)'

Parameters:

companyName - Company name
numResults (optional, default: 5)

Advanced Tools (Optional)

Six additional tools available by updating config URL:

web_search_advanced_exa - Domain/date filters
deep_search_exa - Query expansion
crawling_exa - Full page extraction
people_search_exa - Professional profiles
deep_researcher_start/check - AI research agent

Enable all tools:

mcporter config add exa-full "https://mcp.exa.ai/mcp?tools=web_search_exa,web_search_advanced_exa,get_code_context_exa,deep_search_exa,crawling_exa,company_research_exa,people_search_exa,deep_researcher_start,deep_researcher_check"

# Then use:
mcporter call 'exa-full.deep_search_exa(query: "AI safety research")'

Tips

Web: Use type: "fast" for quick lookup, "deep" for thorough research
Code: Lower tokensNum (1000-2000) for focused, higher (5000+) for comprehensive

Resources

Source

git clone https://github.com/PHY041/claude-agent-skills/blob/main/skills/exa-web-search-free/SKILL.mdView on GitHub

Overview

Exa Web Search (Free) is an AI-powered toolset that lets you perform web searches for news and facts, find code examples and docs from GitHub and Stack Overflow, and conduct company research for business intel. It requires no API key and is configured via mcporter to connect to the Exa MCP endpoint.

How This Skill Works

The skill exposes three core mcporter tools: web_search_exa for web results, get_code_context_exa for code examples and docs, and company_research_exa for business intel. You provide a query and optional parameters (such as numResults, type, or tokensNum); the results are returned as a list of items with title, url, and snippet. Setup involves configuring mcporter to point at the Exa MCP URL (for example, mcporter config add exa https://mcp.exa.ai/mcp).

When to Use It

Need up-to-date web news or factual information.
Looking for code examples or documentation from GitHub or Stack Overflow.
Researching a specific company for market intelligence or vendor analysis.
You want fast web results without setting up API keys.
You want to compare information across web, code, and company sources in one workflow.

Quick Start

Step 1: Verify mcporter is configured for Exa: mcporter list exa
Step 2: Run a search command, e.g., mcporter call 'exa.web_search_exa(query: "latest AI news", numResults: 5)'
Step 3: Inspect results consisting of title, url, and snippet; refine query as needed

Best Practices

Use the default web search for quick lookups; switch to type: 'fast' for speed or 'deep' for thorough research.
For code searches, tune tokensNum to balance depth (1000-2000 for focused results, 5000+ for breadth).
For company searches, specify the exact companyName and adjust numResults to gather a representative set.
Review multiple results and use the provided title/url/snippet to verify relevance before acting.
If you need broader coverage, enable the full Exa toolset (exa-full) and combine web, code, and company searches.

Example Use Cases

mcporter call 'exa.web_search_exa(query: "latest AI news", numResults: 5)'
mcporter call 'exa.get_code_context_exa(query: "React hooks examples", tokensNum: 3000)'
mcporter call 'exa.company_research_exa(companyName: "Anthropic", numResults: 3)'
mcporter call 'exa.web_search_exa(query: "HTTP vs HTTPS security", numResults: 4, type: "fast")'
Enable exa-full and run a deep search: mcporter call 'exa-full.deep_search_exa(query: "AI safety research")'

Frequently Asked Questions

Add this skill to your agents