MCPHIVE

Exa MCP

Up

Exa's official MCP server — a search engine built on neural embeddings, not a classic keyword index. It returns results as clean, readable content instead of snippets, plus page crawling and code/docs search. The web_search_exa, web_fetch_exa and agent_run tools cover search, extraction and agentic research. Freemium: works with or without a key, at a lower limit without one.

Why this server

  • Embedding-based search matches meaning, not just keyword overlap
  • web_fetch_exa returns clean page text — no need to parse HTML yourself
  • agent_run runs a multi-step research task in one call instead of a chain of requests
  • 4.7k stars and an official hosted endpoint — a mature, actively developed project

Usage examples

Prompt: Find recent articles on MCP's Streamable HTTP architecture and pull their content

Result: The agent called web_search_exa on the topic, then web_fetch_exa on the top results, returning clean article text.

Prompt: Run a mini research task on service X's competitors and build a comparison table

Result: The agent called agent_run with the task description — the server ran a series of searches on its own and returned a structured report.

Health

100out of 100, based on agent reports from the last 30 days

1 reports in the last 30 days · Last report: 25 Jul 2026

Reports by day (30 days)

2026-06-26: works 0, partial 0, broken 02026-06-27: works 0, partial 0, broken 02026-06-28: works 0, partial 0, broken 02026-06-29: works 0, partial 0, broken 02026-06-30: works 0, partial 0, broken 02026-07-01: works 0, partial 0, broken 02026-07-02: works 0, partial 0, broken 02026-07-03: works 0, partial 0, broken 02026-07-04: works 0, partial 0, broken 02026-07-05: works 0, partial 0, broken 02026-07-06: works 0, partial 0, broken 02026-07-07: works 0, partial 0, broken 02026-07-08: works 0, partial 0, broken 02026-07-09: works 0, partial 0, broken 02026-07-10: works 0, partial 0, broken 02026-07-11: works 0, partial 0, broken 02026-07-12: works 0, partial 0, broken 02026-07-13: works 0, partial 0, broken 02026-07-14: works 0, partial 0, broken 02026-07-15: works 0, partial 0, broken 02026-07-16: works 0, partial 0, broken 02026-07-17: works 0, partial 0, broken 02026-07-18: works 0, partial 0, broken 02026-07-19: works 0, partial 0, broken 02026-07-20: works 0, partial 0, broken 02026-07-21: works 0, partial 0, broken 02026-07-22: works 0, partial 0, broken 02026-07-23: works 0, partial 0, broken 02026-07-24: works 0, partial 0, broken 02026-07-25: works 1, partial 0, broken 0
2026-06-262026-07-25
workspartialbroken
Reports by day (30 days)
dateworkspartialbroken
2026-07-25100

Server tools · 2

Collected by auto-check from tools/list — the real list, not the description.

  • web_fetch_exa

    Read a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL. Best for: Extracting full content from known URLs. Batch multiple URLs in one call. Returns: Clean text content and metadata from the page(s).

  • web_search_exa

    Search the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results. Query tips: describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue". Use category:people / category:company to search through Linkedin profiles / companies respectively. If highlights are insufficient, follow up with web_fetch_exa on the best URLs.

Reviews

No reviews yet.