Exa
Neural web search that returns full page contents alongside results, which removes a second fetch step for research agents.
What it does
Neural web search that returns full page contents alongside results, which removes a second fetch step for research agents. Better than keyword search for conceptual queries, worse for exact strings and error messages.
Install
Terminal
npx -y exa-mcp-server
Client configuration
Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.
mcp.json
{
"mcpServers": {
"exa": {
"command": "npx",
"args": [
"-y",
"exa-mcp-server"
]
}
}
}
When to use it
Reach for this when the task needs search inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.
Other TypeScript servers
- Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
- Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
- Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude