Skip to main content The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench Explore Tool Discovery

Vertex AI MCP Server

Turn Vertex AI into an enterprise agent

Let your employees delegate real work to Vertex AI across all their apps, under their own identity and permissions.

DrataGPLocalyzeFlipMindtoolsScreenloop

Get Vertex AI to work.
Not just chat.

One connection to StackOne, and Vertex AI gets scoped access to every app your employees use, to act on their behalf.

Connect

Make every system AI-ready

Give your AI access to 470+ managed MCP servers and 28,000+ tested tools. No auth code to write, no API maintenance.

Secure

Keep AI under control

Enforce identity-based access, screen every response for prompt injection, and audit every action.

Optimize

Trust what AI delivers

Keep your agent sharp with lean tool loading and boost reliability with the Falcon execution engine. Pre-synced data for faster context is coming soon.

Connect Vertex AI
to more apps in 4 steps

From auth config to first agent tool call in 5 minutes.

1

Wire StackOne as an MCPToolset in your ADK agent.

In Agent Development Kit (ADK) Python, wrap the StackOne gateway URL in MCPToolset and pass it as a tool on your LlmAgent. Deploy via Agent Engine — available to every agent in your GCP project.

Python — ADK Agent
from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool import (
    MCPToolset, StreamableHTTPConnectionParams,
)

stackone = MCPToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://api.stackone.com/mcp",
        headers={"Authorization": f"Bearer {STACKONE_TOKEN}"},
    )
)

agent = LlmAgent(
    model="gemini-2.5-flash",
    name="enterprise_agent",
    tools=[stackone],
)
View ADK MCP docs (opens in new tab)
2

Connect each SaaS integration in StackOne.

OAuth or API key per app, done once in your dashboard. Tokens stay server-side.

salesforce
workday
stripe
linear
github
Browse all connectors
3

Scope agent actions.

Read-only, specific objects, or per-role exposure. Toggle from the StackOne dashboard.

List records (enabled)
Get record (enabled)
Read related (enabled)
Update record (disabled)
Delete record (disabled)
4

Let your Vertex AI agent call StackOne in plain English.

StackOne maps the agent's tool call to the right action in the right system. Done.

"Sync this week's Salesforce opportunities into BigQuery and open a Linear ticket for any deal blocking the Q3 forecast."

Vertex AI
salesforce_list_opportunities
Completed
linear_create_issue
Completed
team: Revenue Operations
priority: high
result: REV-512 created

Synced 38 Salesforce opportunities to BigQuery. Filed REV-512 for the 4 deals blocking Q3.

Connect Vertex AI to
any Enterprise MCP server

One MCP gateway, 450+ pre-built SaaS connectors Vertex AI can act on right away.

Need another connector? Build one with the AI Connector Builder

Get Vertex AI
to do more across your stack

Cross-app workflows your Vertex AI agent now runs in seconds instead of click-throughs.

Customer 360

> Pull Salesforce account context and join it with BigQuery product usage for the next-best action.

SalesforceKeapZoho CRMPipedriveFreshsalesJustCallPardotAircall
HR & Workforce

> Reconcile Workday hires with their GitHub access in seconds.

UKG ReadyWorkday (Rest and Soap)FactorialHiBobOracle Fusion HCMHumaansSAP SuccessFactorsClockify
Finance & Billing

> Reconcile Stripe revenue with the NetSuite GL for month-end close.

KlaviyoStripeMagentoSquareBigCommerceShopifyEventbriteWooCommerce
Engineering & DevOps

> Open a Linear ticket from a Sentry alert and notify the on-call channel.

Azure DevOpsCloudflareBitbucketGitLabLinearTerraformSupabaseOneLogin

Not everyone on Vertex AI?
Your integration layer stays the same.

The same setup works across AI cloud platforms like Bedrock, watsonx Orchestrate, and every other MCP client.

Explore MCP clients

Frequently Asked Questions

You connect Vertex AI to the StackOne MCP gateway through the Agent Development Kit: wrap the StackOne gateway URL in an MCPToolset with StreamableHTTPConnectionParams, pass it as a tool on your LlmAgent, and deploy via Agent Engine. See the ADK MCP docs. Now part of Gemini Enterprise Agent Platform.
You can connect Vertex AI to 470+ live MCP servers through StackOne, spanning CRM, HRIS, ATS, ticketing, and finance — Salesforce, Workday, Greenhouse, and more. Each is reachable through one gateway URL instead of wiring up servers app by app. Browse the full list in the directory on this page, or build your own.
Google's first-party MCP servers cover Google-owned data (BigQuery, Maps, Cloud SQL via MCP Toolbox, plus Apigee adapters). StackOne adds the other 470+ operational SaaS — every app reachable through one MCPToolset instead of one per app, auth managed once in the dashboard, and tool definitions loaded only when relevant to the prompt.
Credentials sit at three layers: your StackOne API token (embedded in the gateway URL passed to StreamableHTTPConnectionParams headers, stored as a Secret Manager secret in your GCP project), SaaS connector credentials (server-side in your StackOne dashboard), and per-user OAuth tokens scoped to what each person authorized.
Skip the StackOne MCP gateway when any of these is true:
  • Google's first-party MCP servers (BigQuery, Maps, Cloud SQL via MCP Toolbox) cover your apps
  • You use only a handful of actions across a few apps
  • You don't need multi-tenancy or per-action scoping
  • Prompt injection isn't a concern
  • Your provider already does tool discovery and server-side execution

Connect All Your Apps to Vertex AI.

One MCP gateway, 470+ pre-built SaaS connectors. Set up in 5 minutes.