MCP server for Vertex AI and Gemini tools, including grounded answers, documentation research, and filesystem workflows.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add vertex-ai -- node /full/path/to/your/vertex-ai-mcp-server/build/index.js~/.codex/config.toml
[mcp_servers.vertex-ai]
command = "node"
args = ["/full/path/to/your/vertex-ai-mcp-server/build/index.js"]
# codex mcp add vertex-ai -- node /full/path/to/your/vertex-ai-mcp-server/build/index.js~/.cursor/mcp.json
{
"mcpServers": {
"vertex-ai": {
"command": "node",
"args": [
"/full/path/to/your/vertex-ai-mcp-server/build/index.js"
]
}
}
}.vscode/mcp.json
{
"servers": {
"vertex-ai": {
"type": "stdio",
"command": "node",
"args": [
"/full/path/to/your/vertex-ai-mcp-server/build/index.js"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"vertex-ai": {
"command": "node",
"args": [
"/full/path/to/your/vertex-ai-mcp-server/build/index.js"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"vertex-ai": {
"command": "node",
"args": [
"/full/path/to/your/vertex-ai-mcp-server/build/index.js"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"vertex-ai": {
"command": "node",
"args": [
"/full/path/to/your/vertex-ai-mcp-server/build/index.js"
]
}
}
}