How to Use the GUIDEcx MCP in Google ADK

Q: Does the GUIDEcx MCP Server support long-context reasoning with Gemini?

Yes, you can feed thousands of task logs retrieved via listtasks into Gemini's context window. The model uses this data to write summaries or predict project completion dates.

Connect your BigQuery data to customer onboarding by running GUIDEcx tools directly inside your Google ADK agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GUIDEcx MCP to Google ADK

Create your Vinkius account to connect GUIDEcx 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 GUIDEcx with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync data tables with the GUIDEcx MCP Server

Your enterprise data warehouse holds the key to client health. Using this integration, your Gemini agent reads contract data from BigQuery and uses `create_project` to initialize onboarding workspaces instantly. This bridges the gap between raw analytical data and real-world execution. The agent keeps things aligned by running `list_projects` daily. It compares active onboarding pipelines against your customer database to ensure no signed account is left waiting.

Analyze massive task lists with Google ADK

Because Gemini handles massive token contexts, your agent imports entire project boards via `list_tasks` to analyze bottlenecks. It spots patterns in delayed tasks that a human coordinator would easily miss. When the agent identifies a resolved blocker, it executes `update_task` to update the project board. You get accurate, real-time tracking without forcing your implementation team to click through endless dashboards.

Match project tasks to the right resources

Assigning the wrong engineer to a specialized onboarding phase stalls a project for weeks. Your agent checks team availability against active workloads using `list_users` and `list_project_users`. It ensures that complex tasks are routed to team members who actually have open bandwidth. Once work starts, the agent monitors progress by pulling `list_time_records` to flag discrepancies before they impact your margins.

Setup guide

Set up GUIDEcx 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 GUIDEcx 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="GUIDEcx_agent",
    model="gemini-2.0-flash",
    instruction="You have access to GUIDEcx 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 GUIDEcx. 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 GUIDEcx 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 GUIDEcx MCP in Google ADK

Set up your Vinkius endpoint URL as an environment variable in your Google Cloud environment. Then, instantiate the MCP toolset class and pass it directly to your Gemini agent tool array.

Yes, you can build multi-tool agents that query GUIDEcx with `list_time_records` and immediately write those logs to BigQuery. This allows you to build custom financial dashboards without manual exports.

Yes, you can feed thousands of task logs retrieved via `list_tasks` into Gemini's context window. The model uses this data to write summaries or predict project completion dates.

You use the optional tool name filter when defining your MCP toolset in Python. This lets you hide write operations like `update_task` if you only want your agent to read data.

All requests containing your task lists, user directories, and project milestones are processed through Vinkius's zero-trust sandbox. Your API keys are encrypted at rest and never shared with Google or any third-party LLM providers.

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