exa

What exa does, in the publisher's words

From the project README, punctuation lightly normalized · Open the README on GitHub →

Links

• github.com/exa-labs/exa-mcp-server
• https://docs.exa.ai/reference/exa-mcp
• plugin.json (manifest)

Skills · 2

exa-agent

Use Exa Agent for multi-step web research, list-building, enrichment, structured output, run continuation, and coverage validation. Exa Agent can access additional data providers: fiber, financial_datasets, similarweb, baselayer, affiliate, particle, and jinko.

search

Deep research powered by Exa. Use for lead generation, literature reviews, deep dives, competitive analysis, or any query where one search falls short, including phrases like 'research this', 'find everything about', 'find me all', or 'deep dive on'.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

MCP servers · 1

exastreamable-http

https://mcp.exa.ai/mcp?client=agent-plugin

Read from the plugin's own mcp.json. We list environment variable names, never values.

Category

Research & Search. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Keywords

mcp · search · web-search · code-search · exa · research · company-research · linkedin · crawling

Related by publisher and keywords

• perplexityperplexityai

  Real-time web search, reasoning, and research through Perplexity's API

• all-searchRetiredPhysicist

  Live web search and clean page extraction through the AnySearch MCP gateway.

• search1apisuperagents-lab

  Web search, news, page crawl, sitemap, and trending topics via Search1API.

• nimbleNimbleway

  Live web search for AI agents. Find current pages, read any URL, and run research agents that work across many sources and return findings with citations. Includes reusable Extraction Templates for consistently shaped records from known sites, and Web Search Agents for research, enrichment, and dataset building.

• firecrawl777genius

  Community package for Firecrawl MCP. Search, scrape, and parse public web content through Firecrawl's hosted server.

• everyinfraeveryinfra

  Discover and safely use EveryInfra search, structured public data, source-bound cleanup, AI, authorized captcha, number, email, and proxy workflows from supported agent clients.