> ## Documentation Index
> Fetch the complete documentation index at: https://tracecat-codex-docs-secrets-oauth-discoverability.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Exa

> Reference for the Tracecat Exa integration: registered actions, required secrets, expected inputs, and example workflow usage.

## Answer

Action ID: `tools.exa.answer`

Answer a question with Exa search-grounded citations.

Reference: [https://exa.ai/docs/reference/answer](https://exa.ai/docs/reference/answer)

### Secrets

Required secrets:

* `exa`: required values `EXA_API_KEY`.

### Input fields

<ParamField path="query" type="string" required>
  Natural-language question or instructions for the request.
</ParamField>

<ParamField path="outputSchema" type="object | null">
  JSON Schema Draft 7 object for structured answer output.

  Default: `null`.
</ParamField>

<ParamField path="text" type="boolean | null">
  Return full page text in citations when true.

  Default: `null`.
</ParamField>

## Deep research

Action ID: `tools.exa.deep_research`

Run Exa deep-reasoning search for research-style discovery and synthesis.

Reference: [https://exa.ai/docs/changelog/may-2026-api-deprecations](https://exa.ai/docs/changelog/may-2026-api-deprecations)

### Secrets

Required secrets:

* `exa`: required values `EXA_API_KEY`.

### Input fields

<ParamField path="query" type="string" required>
  Natural language research query or instructions.
</ParamField>

<ParamField path="additionalQueries" type="array[string] | null">
  Additional query variations used alongside the main query.

  Default: `null`.
</ParamField>

<ParamField path="compliance" type="string | null">
  Optional Exa enterprise compliance mode.

  Default: `null`.
</ParamField>

<ParamField path="contents" type="object | null">
  Optional Exa contents options nested under the search request contents field.

  Default: `null`.
</ParamField>

<ParamField path="numResults" type="integer | null">
  Number of results to return. Exa supports 1 to 100.

  Default: `null`.
</ParamField>

<ParamField path="outputSchema" type="object | null">
  JSON schema for synthesized output. Supported root types are text and object.

  Default: `null`.
</ParamField>

<ParamField path="systemPrompt" type="string | null">
  Additional instructions that guide synthesized output or search planning.

  Default: `null`.
</ParamField>

## Get contents

Action ID: `tools.exa.get_contents`

Get clean page contents, highlights, summaries, and metadata for URLs or Exa result IDs.

Reference: [https://exa.ai/docs/reference/contents-api-guide-for-coding-agents](https://exa.ai/docs/reference/contents-api-guide-for-coding-agents)

### Secrets

Required secrets:

* `exa`: required values `EXA_API_KEY`.

### Input fields

<ParamField path="urls" type="array[string]" required>
  URLs or Exa result IDs to extract content from.
</ParamField>

<ParamField path="compliance" type="string | null">
  Optional Exa enterprise compliance mode.

  Default: `null`.
</ParamField>

<ParamField path="extras" type="object | null">
  Optional Exa extras options, such as links or imageLinks.

  Default: `null`.
</ParamField>

<ParamField path="highlights" type="boolean | object | null">
  Return extractive key excerpts, or Exa highlight options.

  Default: `null`.
</ParamField>

<ParamField path="livecrawlTimeout" type="integer | null">
  Timeout for livecrawling in milliseconds.

  Default: `null`.
</ParamField>

<ParamField path="maxAgeHours" type="integer | null">
  Maximum age of cached content in hours. Use 0 to always livecrawl or -1 for cache-only.

  Default: `null`.
</ParamField>

<ParamField path="subpageTarget" type="string | array[string] | null">
  Keywords to prioritize when selecting subpages.

  Default: `null`.
</ParamField>

<ParamField path="subpages" type="integer | null">
  Number of subpages to crawl for each URL.

  Default: `null`.
</ParamField>

<ParamField path="summary" type="boolean | object | null">
  Return LLM-generated summaries, or Exa summary options.

  Default: `null`.
</ParamField>

<ParamField path="text" type="boolean | object | null">
  Return full page text as markdown, or Exa text options.

  Default: `true`.
</ParamField>

## Search companies

Action ID: `tools.exa.search_companies`

Search Exa's company index for company profiles and typed company metadata as a second opinion for company-enrichment workflows.

Reference: [https://exa.ai/docs/reference/verticals/company-for-coding-agents](https://exa.ai/docs/reference/verticals/company-for-coding-agents)

### Secrets

Required secrets:

* `exa`: required values `EXA_API_KEY`.

### Input fields

<ParamField path="query" type="string" required>
  Natural language company search query. Encode industry, funding stage, headcount, geography, technology, similarity, and timing constraints in the query string.
</ParamField>

<ParamField path="contents" type="object | null">
  Optional Exa contents options nested under the search request contents field, such as highlights, text, or summary.

  Default: `null`.
</ParamField>

<ParamField path="numResults" type="integer | null">
  Number of company results to return. Exa supports 1 to 100.

  Default: `null`.
</ParamField>

<ParamField path="outputSchema" type="object | null">
  Optional JSON schema for structured output when using deep search modes.

  Default: `null`.
</ParamField>

<ParamField path="type" type="string | null">
  Search method. Exa recommends auto; deep and deep-reasoning also work.

  Default: `"auto"`.
</ParamField>

## Search news

Action ID: `tools.exa.search_news`

Search Exa's news index for current events, journalism, campaign chatter, and executive-protection monitoring.

Reference: [https://exa.ai/docs/reference/verticals/news-for-coding-agents](https://exa.ai/docs/reference/verticals/news-for-coding-agents)

### Secrets

Required secrets:

* `exa`: required values `EXA_API_KEY`.

### Input fields

<ParamField path="query" type="string" required>
  Natural language news query for a topic, company, person, event, domain, product, vulnerability, or campaign artifact.
</ParamField>

<ParamField path="compliance" type="string | null">
  Optional Exa enterprise compliance mode.

  Default: `null`.
</ParamField>

<ParamField path="contents" type="object | null">
  Optional Exa contents options nested under the search request contents field, such as highlights, text, summary, maxAgeHours, subpages, or extras.

  Default: `null`.
</ParamField>

<ParamField path="endPublishedDate" type="string | null">
  ISO 8601 upper bound for published date.

  Default: `null`.
</ParamField>

<ParamField path="excludeDomains" type="array[string] | null">
  Exclude news results from these domains.

  Default: `null`.
</ParamField>

<ParamField path="includeDomains" type="array[string] | null">
  Only return news results from these domains.

  Default: `null`.
</ParamField>

<ParamField path="numResults" type="integer | null">
  Number of news results to return. Exa supports 1 to 100.

  Default: `null`.
</ParamField>

<ParamField path="outputSchema" type="object | null">
  Optional JSON schema for structured output when using Exa synthesis.

  Default: `null`.
</ParamField>

<ParamField path="startPublishedDate" type="string | null">
  ISO 8601 lower bound for published date.

  Default: `null`.
</ParamField>

<ParamField path="type" type="string | null">
  Search method. Exa recommends auto for news; use fast or instant when latency matters.

  Default: `"auto"`.
</ParamField>

## Search people

Action ID: `tools.exa.search_people`

Search Exa's people index for professional profiles as a second opinion for people-enrichment workflows.

Reference: [https://exa.ai/docs/reference/verticals/people-for-coding-agents](https://exa.ai/docs/reference/verticals/people-for-coding-agents)

### Secrets

Required secrets:

* `exa`: required values `EXA_API_KEY`.

### Input fields

<ParamField path="query" type="string" required>
  Natural language people search query. Encode role, skill, company, location, seniority, and other constraints in the query string.
</ParamField>

<ParamField path="contents" type="object | null">
  Optional Exa contents options nested under the search request contents field, such as highlights, text, or summary.

  Default: `null`.
</ParamField>

<ParamField path="numResults" type="integer | null">
  Number of people results to return. Exa supports 1 to 100.

  Default: `null`.
</ParamField>

<ParamField path="outputSchema" type="object | null">
  Optional JSON schema for structured output when using deep search modes.

  Default: `null`.
</ParamField>

<ParamField path="type" type="string | null">
  Search method. Exa recommends auto; deep and deep-reasoning also work.

  Default: `"auto"`.
</ParamField>

## Search the web

Action ID: `tools.exa.search`

Search the web with Exa, with optional advanced filters and content extraction.

Reference: [https://exa.ai/docs/reference/search-api-guide-for-coding-agents](https://exa.ai/docs/reference/search-api-guide-for-coding-agents)

### Secrets

Required secrets:

* `exa`: required values `EXA_API_KEY`.

### Input fields

<ParamField path="query" type="string" required>
  Natural language search query. Supports long, semantically rich descriptions.
</ParamField>

<ParamField path="additionalQueries" type="array[string] | null">
  Additional query variations for deep-search variants.

  Default: `null`.
</ParamField>

<ParamField path="category" type="string | null">
  Optional content category. Known categories include company, people, research paper, news, personal site, and financial report; Exa also accepts other category hints.

  Default: `null`.
</ParamField>

<ParamField path="compliance" type="string | null">
  Optional Exa enterprise compliance mode.

  Default: `null`.
</ParamField>

<ParamField path="contents" type="object | null">
  Optional Exa contents options nested under the search request contents field, such as highlights, text, summary, maxAgeHours, subpages, or extras.

  Default: `null`.
</ParamField>

<ParamField path="endPublishedDate" type="string | null">
  ISO 8601 upper bound for published date. Not supported for company or people category searches.

  Default: `null`.
</ParamField>

<ParamField path="excludeDomains" type="array[string] | null">
  Exclude results from these domains. Not supported for company or people category searches.

  Default: `null`.
</ParamField>

<ParamField path="includeDomains" type="array[string] | null">
  Only return results from these domains. Exa supports domain path filters and subdomain wildcards.

  Default: `null`.
</ParamField>

<ParamField path="moderation" type="boolean | null">
  Filter unsafe content from search results.

  Default: `null`.
</ParamField>

<ParamField path="numResults" type="integer | null">
  Number of results to return. Exa supports 1 to 100.

  Default: `null`.
</ParamField>

<ParamField path="outputSchema" type="object | null">
  JSON schema for synthesized output. Supported root types are text and object.

  Default: `null`.
</ParamField>

<ParamField path="startPublishedDate" type="string | null">
  ISO 8601 lower bound for published date. Not supported for company or people category searches.

  Default: `null`.
</ParamField>

<ParamField path="systemPrompt" type="string | null">
  Additional instructions that guide synthesized output or deep-search planning.

  Default: `null`.
</ParamField>

<ParamField path="type" type="string | null">
  Search method. Exa supports auto, instant, fast, deep-lite, deep, and deep-reasoning.

  Default: `"auto"`.
</ParamField>

<ParamField path="userLocation" type="string | null">
  Two-letter ISO country code used to bias search results.

  Default: `null`.
</ParamField>