How to Use the Fulcrum MCP in Google ADK

Q: How do I set up the Fulcrum MCP Server with Google ADK?

You'll instantiate the McpToolset from the Google ADK library, pointing it to your Vinkius server URL. Then you pass that toolset to your LlmAgent constructor. You can also filter which tools are exposed if you only need a subset.

Let your Google ADK agent work with your Fulcrum field data. Query records directly and sync results with your Google Cloud ecosystem.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fulcrum MCP to Google ADK

Create your Vinkius account to connect Fulcrum to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Fulcrum with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Put Fulcrum Data into BigQuery

This is the most direct way to get your field data into your Google Cloud warehouse. Your Gemini agent can use `query_records_sql` to pull specific datasets from Fulcrum and then push that data straight into a BigQuery table. No more manual CSV exports and imports. Because Google ADK is designed for long-context reasoning, you can build sophisticated ETL pipelines. The agent can fetch the schema with `get_form_schema`, create a matching table in BigQuery, and then run a `query_records_sql` job to populate it.

Give Gemini Real-World Context

An agent is only as good as its data. This MCP Server gives your Gemini agent a direct line to your field operations. It can check project status by calling `list_field_records` for a specific form or get the details of a single entry with `get_record_details`. This turns your agent from a general-purpose tool into a project-aware assistant. It can answer questions like "How many safety inspections were completed today?" by querying Fulcrum directly, giving you real-time operational intelligence.

Build Enterprise Workflows with Google ADK

Go beyond simple queries. You can build agents that manage your Fulcrum environment. Have an agent create new records via `create_record` based on alerts from Google Cloud Monitoring. Or, build an auditing agent that periodically checks `list_organization_members` against your company directory. This MCP server gives your agent the tools to act. It's not just about reading data. It's about creating, updating, and managing your operational dataset programmatically.

Setup guide

Set up Fulcrum MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Fulcrum tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Fulcrum_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Fulcrum tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Fulcrum. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Fulcrum now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Fulcrum MCP in Google ADK

You'll instantiate the `McpToolset` from the Google ADK library, pointing it to your Vinkius server URL. Then you pass that toolset to your `LlmAgent` constructor. You can also filter which tools are exposed if you only need a subset.

Yes. Once your Google ADK agent gets data from Fulcrum using tools like `list_field_records`, it's just data in your Python code. You can then use other Google Cloud client libraries to send it to Pub/Sub, Cloud Storage, or Vertex AI.

If a tool call to the Fulcrum MCP Server fails, like a bad SQL query in `query_records_sql`, the server returns an error. The Google ADK framework will raise that as an exception in your agent's code. You should wrap your tool calls in try/except blocks to handle these cases.

It's all about efficiency. Instead of fetching thousands of records and filtering them in your agent, `query_records_sql` runs the logic on the data source. This is critical for Gemini's long-context abilities, as it frees up the context window for reasoning instead of just holding raw data.

Your agent works with sensitive field data, form schemas, and user information from Fulcrum. Every request is authenticated via your Vinkius token over a secure connection. The Vinkius platform processes each request in a dedicated, single-use sandbox, ensuring your data isn't co-mingled or persisted after the job is done.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript