Search, documentation retrieval, code analysis and architecture research using Vertex AI or the Gemini API.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add google-ai-search --env GEMINI_API_KEY='<GEMINI_API_KEY>' -- npx -y google-ai-search-mcp~/.codex/config.toml
[mcp_servers.google-ai-search]
command = "npx"
args = ["-y", "google-ai-search-mcp"]
env = { GEMINI_API_KEY = "<GEMINI_API_KEY>" }
# codex mcp add google-ai-search --env GEMINI_API_KEY='<GEMINI_API_KEY>' -- npx -y google-ai-search-mcp~/.cursor/mcp.json
{
"mcpServers": {
"google-ai-search": {
"command": "npx",
"args": [
"-y",
"google-ai-search-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"google-ai-search": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"google-ai-search-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"google-ai-search": {
"command": "npx",
"args": [
"-y",
"google-ai-search-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"google-ai-search": {
"command": "npx",
"args": [
"-y",
"google-ai-search-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"google-ai-search": {
"command": "npx",
"args": [
"-y",
"google-ai-search-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>"
}
}
}
}Environment variables
GEMINI_API_KEY
Replace the placeholders with your own credentials and keep them out of version control.