Loading...
Loading...
Neural 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.
npx skill4agent add affaan-m/everything-claude-code exa-search~/.claude.json"exa-web-search": {
"command": "npx",
"args": [
"-y",
"exa-mcp-server",
"tools=web_search_exa,web_search_advanced_exa,get_code_context_exa,crawling_exa,company_research_exa,people_search_exa,deep_researcher_start,deep_researcher_check"
],
"env": { "EXA_API_KEY": "YOUR_EXA_API_KEY_HERE" }
}tools=...web_search_exa(query: "latest AI developments 2026", numResults: 5)| Param | Type | Default | Notes |
|---|---|---|---|
| string | required | Search query |
| number | 8 | Number of results |
web_search_advanced_exa(
query: "React Server Components best practices",
numResults: 5,
includeDomains: ["github.com", "react.dev"],
startPublishedDate: "2025-01-01"
)| Param | Type | Default | Notes |
|---|---|---|---|
| string | required | Search query |
| number | 8 | Number of results |
| string[] | none | Limit to specific domains |
| string[] | none | Exclude specific domains |
| string | none | ISO date filter (start) |
| string | none | ISO date filter (end) |
get_code_context_exa(query: "Python asyncio patterns", tokensNum: 3000)| Param | Type | Default | Notes |
|---|---|---|---|
| string | required | Code or API search query |
| number | 5000 | Content tokens (1000-50000) |
company_research_exa(companyName: "Anthropic", numResults: 5)| Param | Type | Default | Notes |
|---|---|---|---|
| string | required | Company name |
| number | 5 | Number of results |
people_search_exa(query: "AI safety researchers at Anthropic", numResults: 5)crawling_exa(url: "https://example.com/article", tokensNum: 5000)| Param | Type | Default | Notes |
|---|---|---|---|
| string | required | URL to extract |
| number | 5000 | Content tokens |
# Start research
deep_researcher_start(query: "comprehensive analysis of AI code editors in 2026")
# Check status (returns results when complete)
deep_researcher_check(researchId: "<id from start>")web_search_exa(query: "Node.js 22 new features", numResults: 3)get_code_context_exa(query: "Rust error handling patterns Result type", tokensNum: 3000)company_research_exa(companyName: "Vercel", numResults: 5)
web_search_advanced_exa(query: "Vercel funding valuation 2026", numResults: 3)# Start async research
deep_researcher_start(query: "WebAssembly component model status and adoption")
# ... do other work ...
deep_researcher_check(researchId: "<id>")web_search_exaweb_search_advanced_exatokensNumcompany_research_exaweb_search_advanced_exacrawling_exadeep_researcher_startdeep-researchmarket-research