How to Use the Jibble MCP in Google ADK

Q: How do I set up the Jibble MCP toolset within the Google ADK?

Install google-adk and initialize McpToolset using your Vinkius HTTP transport URL. You can then pass this toolset directly to your LlmAgent to expose all ten time-tracking endpoints to Gemini.

Q: Can Google ADK agents filter specific Jibble tools for security?

Yes, you can use the optional toolnames parameter in the ADK to restrict which tools are exposed. For example, you can allow access to listprojects while completely blocking access to sensitive personnel endpoints.

Q: How is my Jibble group and client metadata protected?

All requests routed through this MCP Server to listgroups and listclients run through secure, isolated sandboxes on Vinkius. Your operational structures and client names are never cached, keeping your corporate hierarchy completely confidential.

Connect Google ADK agents to Jibble to analyze workforce distribution and feed live time logs directly into your BigQuery pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jibble MCP to Google ADK

Create your Vinkius account to connect Jibble 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 Jibble with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync Jibble logs with BigQuery using Google ADK

Gemini's massive context window allows your agent to process months of attendance records in a single turn. By calling `list_time_entries` via this MCP Server, the agent can pull thousands of rows, analyze patterns, and instantly export structured summaries to your Google Cloud storage. You can combine this with BigQuery SQL queries to map logged hours against actual business revenue. The agent manages the entire pipeline, ensuring your resource allocation data matches your financial projections.

Verify team distribution across physical job sites

Field operations require constant verification to ensure workers are logging hours from authorized zones. Your agent can execute `list_locations` to retrieve active geofences and cross-reference them with actual worker coordinates. If a discrepancy is found, the agent queries `get_person` to identify the supervisor assigned to that specific site. This allows your enterprise system to flag compliance issues automatically without requiring manual payroll audits.

Organize operational metadata for large workforces

Managing thousands of employees across regional offices requires clean grouping structures. This MCP Server integration allows Gemini agents to query `list_groups` alongside `list_activities` to understand how different departments spend their workdays. Whether you need to audit client-facing hours using `list_clients` or internal development tasks, the agent structures the raw metadata cleanly. It translates messy operational logs into clear, actionable reports for HR leadership.

Setup guide

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

Install `google-adk` and initialize `McpToolset` using your Vinkius HTTP transport URL. You can then pass this toolset directly to your `LlmAgent` to expose all ten time-tracking endpoints to Gemini.

Yes, you can use the optional `tool_names` parameter in the ADK to restrict which tools are exposed. For example, you can allow access to `list_projects` while completely blocking access to sensitive personnel endpoints.

Gemini's long-context capabilities allow the agent to ingest massive outputs from `list_time_entries` without running out of memory. This makes it easy to analyze entire company work logs in a single prompt.

Yes, the integration supports both standard input/output (Stdio) and HTTP transport mechanisms. This flexibility allows you to deploy your tracking agents in serverless cloud functions or local terminal environments.

All requests routed through this MCP Server to `list_groups` and `list_clients` run through secure, isolated sandboxes on Vinkius. Your operational structures and client names are never cached, keeping your corporate hierarchy completely confidential.

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