Community MCP server for Exa, a neural search engine that understands meaning rather than keywords. Agents can perform semantic web searches, get auto-summarized content, find similar pages, and extract content from URLs. Uses embeddings-based search for more relevant results than keyword matching. Ideal for research agents, content discovery, and finding semantically related resources.
npx -y exa-mcp
{
"mcpServers": {
"exa": {
"env": {
"EXA_API_KEY": "your-api-key"
},
"args": [
"-y",
"exa-mcp"
],
"command": "npx"
}
}
}Get page contents via Exa
{
"type": "object",
"required": [
"urls"
],
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
}
}
}
}// Input
{
"urls": [
"https://example.com"
]
}// Output
{
"results": [
{
"url": "https://example.com",
"text": "Page content..."
}
]
}Search web with Exa AI
{
"type": "object",
"required": [
"query"
],
"properties": {
"type": {
"type": "string"
},
"query": {
"type": "string"
},
"num_results": {
"type": "integer"
}
}
}// Input
{
"type": "neural",
"query": "best MCP servers 2026",
"num_results": 5
}// Output
{
"results": [
{
"url": "https://example.com",
"score": 0.95,
"title": "Top MCP Servers"
}
]
}Community MCP server for Exa, a neural search engine that understands meaning rather than keywords. Agents can perform semantic web searches, get auto-summarized content, find similar pages, and extract content from URLs. Uses embeddings-based search for more relevant results than keyword matching. Ideal for research agents, content discovery, and finding semantically related resources.
Exa provides 2 tools including get_contents, search.
Exa offers a free tier with 200 calls per month. For higher usage, paid plans start at €0/month.
You can install Exa using the following command: npx -y exa-mcp. After installation, add the provided config snippet to your Claude Desktop or Cursor configuration.
Exa is listed under the Data & Analytics category in the AgentForge MCP registry.
Exa has a current uptime of 99.8% with an average response time of 400ms.
To connect Exa, click the "Connect Agent" button on this page to get the configuration snippet. Add it to your MCP client (Claude Desktop, Cursor, or any MCP-compatible tool). Your AI agent will then have access to all of Exa's tools via the Model Context Protocol.