MCP Deep Research is a tool that allows you to search the web for information. It is built with the Model Context Protocol and the Tavily API.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add deep-research --env TAVILY_API_KEY='<TAVILY_API_KEY>' -- npx -y mcp-deep-research@latest~/.codex/config.toml
[mcp_servers.deep-research]
command = "npx"
args = ["-y", "mcp-deep-research@latest"]
env = { TAVILY_API_KEY = "<TAVILY_API_KEY>" }
# codex mcp add deep-research --env TAVILY_API_KEY='<TAVILY_API_KEY>' -- npx -y mcp-deep-research@latest~/.cursor/mcp.json
{
"mcpServers": {
"deep-research": {
"command": "npx",
"args": [
"-y",
"mcp-deep-research@latest"
],
"env": {
"TAVILY_API_KEY": "<TAVILY_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"deep-research": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-deep-research@latest"
],
"env": {
"TAVILY_API_KEY": "<TAVILY_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"deep-research": {
"command": "npx",
"args": [
"-y",
"mcp-deep-research@latest"
],
"env": {
"TAVILY_API_KEY": "<TAVILY_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"deep-research": {
"command": "npx",
"args": [
"-y",
"mcp-deep-research@latest"
],
"env": {
"TAVILY_API_KEY": "<TAVILY_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"deep-research": {
"command": "npx",
"args": [
"-y",
"mcp-deep-research@latest"
],
"env": {
"TAVILY_API_KEY": "<TAVILY_API_KEY>"
}
}
}
}Environment variables
TAVILY_API_KEY
Replace the placeholders with your own credentials and keep them out of version control.