Exa Search

Exa MCP Search

Use this skill when online search, page fetch, code/docs lookup, company research, people research, or Exa MCP parameter checks are needed.

Current Source Of Truth

• Hosted MCP endpoint: https://mcp.exa.ai/mcp
• Official source: exa-labs/exa-mcp-server
• Current npm package checked: exa-mcp-server@3.2.1
• Tool schemas can change. Before adding new parameters, verify with:

mcporter list 'https://mcp.exa.ai/mcp?tools=web_search_exa,web_search_advanced_exa,web_fetch_exa' --schema

Tool Choice

Core Parameters

web_search_exa

• query required: semantically rich natural-language query. Can include category:company or category:people.
• numResults optional: default 10.
• No type, livecrawl, contextMaxCharacters, or tokensNum on current hosted schema.

{"query":"latest AI safety research June 2026","numResults":10}

web_search_advanced_exa

• query required.
• Common optional filters: numResults, type (auto | fast | instant), category, includeDomains, excludeDomains, startPublishedDate, endPublishedDate, startCrawlDate, endCrawlDate, includeText, excludeText, userLocation, moderation, additionalQueries.
• Content controls: textMaxCharacters, contextMaxCharacters, enableSummary, summaryQuery, enableHighlights, highlightsMaxCharacters, highlightsQuery, maxAgeHours, livecrawlTimeout, subpages, subpageTarget.
• Categories include company, research paper, news, pdf, github, personal site, people, financial report.

{
  "query":"Anthropic funding valuation 2026",
  "category":"news",
  "includeDomains":["techcrunch.com","bloomberg.com"],
  "startPublishedDate":"2026-01-01",
  "numResults":10,
  "type":"auto",
  "enableHighlights":true
}

web_fetch_exa

• urls required: array of URLs. A single string may also be accepted by the server.
• maxCharacters optional: default 3000.

{"urls":["https://docs.exa.ai/reference"],"maxCharacters":5000}

Deprecated But Still Available

• get_code_context_exa: use web_search_exa instead. Current schema is query, numResults; old tokensNum is obsolete.
• company_research_exa: use web_search_advanced_exa with category:"company" instead. Schema is companyName, numResults; default 3.
• people_search_exa: use web_search_advanced_exa with category:"people" instead.
• crawling_exa: use web_fetch_exa instead.
• deep_search_exa: use web_search_advanced_exa instead; may require user-provided Exa API key and may not register on anonymous hosted MCP.
• deep_researcher_start / deep_researcher_check: deprecated; use Exa Research API directly when needed.

Invocation Examples

URL="https://mcp.exa.ai/mcp?tools=web_search_exa,web_search_advanced_exa,web_fetch_exa"
npx -y mcporter call "$URL.web_search_exa" query="latest AI safety research" numResults:=10
npx -y mcporter call "$URL.web_search_advanced_exa" query="AI infrastructure startups" category=company numResults:=20
npx -y mcporter call "$URL.web_fetch_exa" urls:='["https://docs.exa.ai/reference"]' maxCharacters:=5000

For mcporter call --http-url style, keep JSON args aligned with the same schemas.

Research Practice

• For simple lookup, run one targeted web_search_exa call.
• For dated/current questions, calculate exact date ranges first and pass startPublishedDate / endPublishedDate through web_search_advanced_exa.
• For source-heavy tasks, fetch only the best URLs with web_fetch_exa; do not dump raw results into the final answer.
• For company/people/paper/news workflows, prefer web_search_advanced_exa categories rather than deprecated specialized tools.
• Mention source uncertainty when Exa returns sparse, conflicting, or old results.

References

• Tool fields: references/exa-tools.md

Exa MCP Tools And Parameters

Snapshot checked against:

• Hosted endpoint: https://mcp.exa.ai/mcp
• Official repo: exa-labs/exa-mcp-server@9ea4ba3e67f87c462c3e06b192470e837ed9009e
• npm package: exa-mcp-server@3.2.1
• Date checked: 2026-06-19

Base URL

• Base: https://mcp.exa.ai/mcp
• Select tools: ?tools=tool_a,tool_b,...
• API key: ?exaApiKey=YOUR_EXA_API_KEY, Authorization: Bearer ..., or EXA_API_KEY for local npm.
• Anonymous hosted use works but has rate limits and may not register API-key-only tools.

Enabled By Default

Off By Default

Deprecated Tools

web_search_advanced_exa Schema

Required:

• query: string

Optional:

• Search tuning: numResults, type (auto | fast | instant)
• Category: company, research paper, news, pdf, github, personal site, people, financial report
• Domain filters: includeDomains, excludeDomains
• Date filters: startPublishedDate, endPublishedDate, startCrawlDate, endCrawlDate
• Text filters: includeText, excludeText
• Geo/safety: userLocation, moderation
• Query expansion: additionalQueries
• Content: textMaxCharacters, contextMaxCharacters, enableSummary, summaryQuery, enableHighlights, highlightsMaxCharacters, highlightsNumSentences, highlightsPerUrl, highlightsQuery
• Freshness/fetch: maxAgeHours, livecrawlTimeout
• Subpages: subpages, subpageTarget

Deprecated/compat details:

• highlightsNumSentences and highlightsPerUrl are deprecated in official source comments; prefer highlightsMaxCharacters.
• livecrawl is not a direct exposed parameter on current hosted web_search_exa; use advanced freshness controls (maxAgeHours, livecrawlTimeout) when needed.
• Old local docs mentioning tokensNum for get_code_context_exa are obsolete.

Minimal MCP Schema Check

mcporter list 'https://mcp.exa.ai/mcp?tools=web_search_exa,web_search_advanced_exa,web_fetch_exa,get_code_context_exa,company_research_exa,people_search_exa' --schema --json

Expected hosted anonymous tools from that request on 2026-06-19:

• web_search_exa
• web_search_advanced_exa
• company_research_exa
• web_fetch_exa
• people_search_exa
• get_code_context_exa

deep_search_exa was requested separately but did not register anonymously, matching official source behavior that requires a user-provided API key.