# Exa — MCP Server

> Give an agent live web search and clean page reads — no API key to get started.

**Source:** https://mcpplaygroundonline.com/mcp-servers/exa  
**Transport:** http  
**Requires auth:** No

---

## What it does

Exa's server is deliberately small — two tools rather than the sprawling surfaces common elsewhere — and that focus is the point. `web_search_exa` searches the live web and returns clean, ready-to-use content rather than a list of links a model then has to fetch and parse. `web_fetch_exa` reads any URL and returns it as clean markdown, which is the natural follow-up when a search highlight is not enough or when you already know the page you want. The pairing maps neatly onto how an agent actually researches: search broadly, then read deeply on the two or three results that matter. Because the server reports itself as exa-search-server with Exa's own metadata and website, there is no ambiguity about provenance.

## Tools exposed

- web_search_exa — search the web for any topic and get clean, ready-to-use content back
- web_fetch_exa — read a webpage's full content as clean markdown, for any URL

## Example queries you can run

- "Search for what changed in the MCP specification this year and summarise the breaking changes."
- "Find three recent independent benchmarks of AI tool calling and compare their methodology."
- "Read this documentation page and tell me the exact auth flow it describes."
- "Who are the main competitors in this space right now, and what does each claim to do differently?"

## Details

- **Recommended model:** anthropic/claude-haiku-4.5 — Only two tools, so selection is trivial and the work is summarising what comes back. Haiku handles that at a fraction of the cost of a frontier model.
- **Transport:** http
- **Authentication:** Not required — None for the hosted endpoint — it answers an initialize handshake unauthenticated. An Exa API key raises limits for heavier use.
- **Hosted endpoint:** https://mcp.exa.ai/mcp
- **Official source:** [Exa MCP documentation](https://docs.exa.ai/reference/exa-mcp)

## Connecting to Exa

### Connection examples

**Hosted endpoint**

```
https://mcp.exa.ai/mcp
```

Streamable HTTP. Responds to initialize with no credential, which makes it a genuinely good server to test a client against.

### Client configuration

**Any MCP client**

No credential block needed — just the URL.

```
{
  "mcpServers": {
    "exa": {
      "type": "http",
      "url": "https://mcp.exa.ai/mcp"
    }
  }
}
```

## Frequently asked questions

### Does the Exa MCP server need an API key?

Not to get started. The hosted endpoint at https://mcp.exa.ai/mcp completes an MCP initialize handshake with no credential at all, which is rare — almost every hosted server answers 401 first. That makes it one of the easiest real servers to point a new client at. An Exa API key is the route to higher limits once you are past experimenting.

### What tools does it expose?

Two: `web_search_exa`, which searches the live web and returns clean content rather than bare links, and `web_fetch_exa`, which reads any URL as clean markdown. That is the whole surface. The restraint is deliberate and it helps — with two tools, every model picks correctly, which is not true of servers exposing hundreds.

### How is this different from Brave Search or Tavily?

All three give an agent web access and all three are worth testing on your own workload. The distinction that matters in practice is what comes back: Exa returns cleaned, ready-to-use content and pairs search with a dedicated markdown fetch tool, which suits research workflows where the model needs to actually read sources. Run the same prompt against each in Agent Studio — result quality varies more by query type than any comparison table can capture.

### Is it a good server for testing an MCP client?

Yes, and it is worth knowing about for that reason alone. Because it needs no auth, it removes the credential variable when you are debugging a client — if your client cannot connect to Exa, the problem is your client, not your token. For deliberately awkward cases, pair it with our mock servers, which return errors and nested schemas on demand.

### Can the model read pages it finds, or only see snippets?

It can read them. `web_fetch_exa` exists precisely for the follow-up step: search returns highlights, and when those are insufficient the model fetches the full page as markdown. This two-step pattern is why the server works well for research tasks rather than only fact-lookup, and it is worth writing prompts that expect it.

---

_Test this server across 40+ models on MCP Playground: https://mcpplaygroundonline.com/mcp-servers/exa — free, no install._