exa-search
starsforks
How to install exa-search?
affaan-m/ecc/exa-search
$npx -y skills add affaan-m/ECC --skill exa-searchNeural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
SKILL.md
| 1 | # Exa Search |
| 2 | |
| 3 | Neural search for web content, code, companies, and people via the Exa MCP server. |
| 4 | |
| 5 | ## When to Activate |
| 6 | |
| 7 | - User needs current web information or news |
| 8 | - Searching for code examples, API docs, or technical references |
| 9 | - Researching companies, competitors, or market players |
| 10 | - Finding professional profiles or people in a domain |
| 11 | - Running background research for any development task |
| 12 | - User says "search for", "look up", "find", or "what's the latest on" |
| 13 | |
| 14 | ## MCP Requirement |
| 15 | |
| 16 | Exa MCP server must be configured. Add to `~/.claude.json`: |
| 17 | |
| 18 | ```json |
| 19 | "exa-web-search": { |
| 20 | "command": "npx", |
| 21 | "args": ["-y", "exa-mcp-server"], |
| 22 | "env": { "EXA_API_KEY": "YOUR_EXA_API_KEY_HERE" } |
| 23 | } |
| 24 | ``` |
| 25 | |
| 26 | Get an API key at [exa.ai](https://exa.ai). |
| 27 | |
| 28 | ## Core Tools |
| 29 | |
| 30 | ### web_search_exa |
| 31 | General web search for current information, news, or facts. |
| 32 | |
| 33 | ``` |
| 34 | web_search_exa(query: "latest AI developments 2026", numResults: 5) |
| 35 | ``` |
| 36 | |
| 37 | **Parameters:** |
| 38 | |
| 39 | | Param | Type | Default | Notes | |
| 40 | |-------|------|---------|-------| |
| 41 | | `query` | string | required | Search query | |
| 42 | | `numResults` | number | 8 | Number of results | |
| 43 | |
| 44 | ### web_search_advanced_exa |
| 45 | Filtered search with domain and date constraints. |
| 46 | |
| 47 | ``` |
| 48 | web_search_advanced_exa( |
| 49 | query: "React Server Components best practices", |
| 50 | numResults: 5, |
| 51 | includeDomains: ["github.com", "react.dev"], |
| 52 | startPublishedDate: "2025-01-01" |
| 53 | ) |
| 54 | ``` |
| 55 | |
| 56 | **Parameters:** |
| 57 | |
| 58 | | Param | Type | Default | Notes | |
| 59 | |-------|------|---------|-------| |
| 60 | | `query` | string | required | Search query | |
| 61 | | `numResults` | number | 8 | Number of results | |
| 62 | | `includeDomains` | string[] | none | Limit to specific domains | |
| 63 | | `excludeDomains` | string[] | none | Exclude specific domains | |
| 64 | | `startPublishedDate` | string | none | ISO date filter (start) | |
| 65 | | `endPublishedDate` | string | none | ISO date filter (end) | |
| 66 | |
| 67 | ### get_code_context_exa |
| 68 | Find code examples and documentation from GitHub, Stack Overflow, and docs sites. |
| 69 | |
| 70 | ``` |
| 71 | get_code_context_exa(query: "Python asyncio patterns", tokensNum: 3000) |
| 72 | ``` |
| 73 | |
| 74 | **Parameters:** |
| 75 | |
| 76 | | Param | Type | Default | Notes | |
| 77 | |-------|------|---------|-------| |
| 78 | | `query` | string | required | Code or API search query | |
| 79 | | `tokensNum` | number | 5000 | Content tokens (1000-50000) | |
| 80 | |
| 81 | ### company_research_exa |
| 82 | Research companies for business intelligence and news. |
| 83 | |
| 84 | ``` |
| 85 | company_research_exa(companyName: "Anthropic", numResults: 5) |
| 86 | ``` |
| 87 | |
| 88 | **Parameters:** |
| 89 | |
| 90 | | Param | Type | Default | Notes | |
| 91 | |-------|------|---------|-------| |
| 92 | | `companyName` | string | required | Company name | |
| 93 | | `numResults` | number | 5 | Number of results | |
| 94 | |
| 95 | ### people_search_exa |
| 96 | Find professional profiles and bios. |
| 97 | |
| 98 | ``` |
| 99 | people_search_exa(query: "AI safety researchers at Anthropic", numResults: 5) |
| 100 | ``` |
| 101 | |
| 102 | ### crawling_exa |
| 103 | Extract full page content from a URL. |
| 104 | |
| 105 | ``` |
| 106 | crawling_exa(url: "https://example.com/article", tokensNum: 5000) |
| 107 | ``` |
| 108 | |
| 109 | **Parameters:** |
| 110 | |
| 111 | | Param | Type | Default | Notes | |
| 112 | |-------|------|---------|-------| |
| 113 | | `url` | string | required | URL to extract | |
| 114 | | `tokensNum` | number | 5000 | Content tokens | |
| 115 | |
| 116 | ### deep_researcher_start / deep_researcher_check |
| 117 | Start an AI research agent that runs asynchronously. |
| 118 | |
| 119 | ``` |
| 120 | # Start research |
| 121 | deep_researcher_start(query: "comprehensive analysis of AI code editors in 2026") |
| 122 | |
| 123 | # Check status (returns results when complete) |
| 124 | deep_researcher_check(researchId: "<id from start>") |
| 125 | ``` |
| 126 | |
| 127 | ## Usage Patterns |
| 128 | |
| 129 | ### Quick Lookup |
| 130 | ``` |
| 131 | web_search_exa(query: "Node.js 22 new features", numResults: 3) |
| 132 | ``` |
| 133 | |
| 134 | ### Code Research |
| 135 | ``` |
| 136 | get_code_context_exa(query: "Rust error handling patterns Result type", tokensNum: 3000) |
| 137 | ``` |
| 138 | |
| 139 | ### Company Due Diligence |
| 140 | ``` |
| 141 | company_research_exa(companyName: "Vercel", numResults: 5) |
| 142 | web_search_advanced_exa(query: "Vercel funding valuation 2026", numResults: 3) |
| 143 | ``` |
| 144 | |
| 145 | ### Technical Deep Dive |
| 146 | ``` |
| 147 | # Start async research |
| 148 | deep_researcher_start(query: "WebAssembly component model status and adoption") |
| 149 | # ... do other work ... |
| 150 | deep_researcher_check(researchId: "<id>") |
| 151 | ``` |
| 152 | |
| 153 | ## Tips |
| 154 | |
| 155 | - Use `web_search_exa` for broad queries, `web_search_advanced_exa` for filtered results |
| 156 | - Lower `tokensNum` (1000-2000) for focused code snippets, higher (5000+) for comprehensive context |
| 157 | - Combine `company_research_exa` with `web_search_advanced_exa` for thorough company analysis |
| 158 | - Use `crawling_exa` to get full content from specific URLs found in search results |
| 159 | - `deep_researcher_start` is best for comprehensive topics that benefit from AI synthesis |
| 160 | |
| 161 | ## Related Skills |
| 162 | |
| 163 | - `deep-research` — Full research workflow using firecrawl + exa together |
| 164 | - `market-research` — Business-oriented research with decision frameworks |
People who liked this also viewed
6 picksType
- azure-aiUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector searSkillsJul 2026
- just-scrapeSearch, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON fromSkillsJul 2026
- firecrawlCLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agentsSkillsJul 2026
- firecrawl-searchWeb search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "SkillsJul 2026
- firecrawl-agentAI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract pricing tiers, producSkillsJul 2026
- firecrawl-mapDiscover and list all URLs on a website, with optional search filtering. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where sSkillsJul 2026
