Exa Search
AI-native web search and page crawling — find and read live web pages with semantic, embeddings-based search. Works out of the box; connect an Exa API key to lift rate limits.
What Exa Search exposes.
Every tool below is one this server advertised the last time Omniio refreshed it, under the exa__ namespace. Your agent never loads them all — it searches, and gets the few that match.
exa__web_fetch_exa2 arguments · 1 required
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).
Required
urlsexa__web_search_exa2 arguments · 1 required
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.
Required
query
Three steps, and the last one is not yours.
Point a client at Omniio
One URL, authorized once by your client. If you already use Omniio, this step is done.
Exa Search is already on
It needs no credential, so it is on for every account from the first call.
Ask for what you need
The agent searches, reads the one schema it picked, and runs it. You do not name the tool.
claude mcp add --transport http omniio https://mcp.omniio.devOthers in the same category.
They share the endpoint, so having more than one on costs you nothing in context — the search decides which is relevant.
