> This page is for Agent Handler.

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.merge.dev/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.merge.dev/_mcp/server.

# Exa

**Authentication:** API key. See [Magic Link](/merge-agent-handler/features/magic-link) for the runtime auth flow.

## Sample use cases

* Find research papers on transformer interpretability published since 2024.
* Search the web for case studies of teams adopting MCP-based agent tooling.
* Surface recent news articles mentioning our top 5 competitors.

## Available Tools

#### answer

AI-generated answer with web citations. Supports exa and exa-pro models. Optional system prompt and structured output via output\_schema (JSON Schema Draft 7).

#### context

Code-focused search across GitHub, docs, Stack Overflow. Returns code snippets and documentation relevant to the query. Max 100000 output tokens.

#### get\_contents

Extract text, highlights, and summaries from URLs. Supports livecrawl for fresh content. Returns per-URL status tracking for partial failures.

#### start\_research

Start an async deep research job. Returns a research\_id to poll with get\_research\_status. Models: exa-research-fast (quick), exa-research (balanced), exa-research-pro (most capable).

#### get\_research\_status

Poll a research job for status and results. Status: pending, running, completed, failed, canceled. Output available when completed.

#### search

Semantic/keyword web search. Supports neural, fast, auto, deep, instant types. Filter by domain, date, text, category. Include text/highlights/summaries via contents.

#### find\_similar

Find pages similar to a URL. Same filters as search plus exclude\_source\_domain. Returns ranked results with optional content extraction.

#### create\_webset

Create a persistent search collection with enrichments. Define a search query and enrichment configs to extract structured data from results.

#### list\_websets

List websets with cursor pagination. Use cursor from page\_info for next page. Returns webset IDs, statuses, and search/enrichment configs.

#### get\_webset

Get webset details by ID including status, search configs, and enrichments. Use list\_websets to find valid IDs.

#### delete\_webset

Delete a webset permanently. This cannot be undone. Use list\_websets to find valid IDs.

#### list\_webset\_items

List items in a webset with cursor pagination. Returns items with URLs, titles, and enrichment results. Use get\_webset to verify the webset exists.