How to Use the Mela MCP in Google ADK

Q: How do I connect Google ADK to the Mela MCP Server?

Initialize McpToolset with your HTTP server parameters and pass it to your LlmAgent. The ADK handles the connection, exposing tools like createactivity to Gemini.

Q: Can I restrict which Mela tools Google ADK can access?

Yes, you can use the toolnames filter when setting up your toolset. This lets you limit the agent to harmless tools like listactivities while blocking write tools.

Q: How does Google ADK handle long-context reasoning with Mela data?

The ADK passes outputs from listchecklists directly into Gemini's large context window. This allows the model to analyze hundreds of pages of site logs at once without losing track of details.

Feed live job site data from Mela directly into your Google ADK enterprise workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mela MCP to Google ADK

Create your Vinkius account to connect Mela 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 Mela with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze job site history in Google ADK

This integration exposes `list_activities` and `list_checklists` to Gemini models via the Google ADK. Gemini's massive 1M token context window lets the Google ADK agent ingest months of historical Mela site logs in one go. You get deep analysis of project bottlenecks without hitting context limits. The Google ADK agent pulls the complete Mela checklist history and compares it against current activity logs. Gemini spots operational patterns, like why concrete pours always stall on Tuesdays. Instead of basic status summaries, you receive highly actionable operation plans.

Sync Mela MCP Server data with BigQuery

The MCP Server allows Google ADK agents to fetch live accounting metrics using `get_accounting_data`. Enterprise developers can pipe this Mela data directly into BigQuery or Vertex AI pipelines. It connects your field operations directly to your cloud data warehouse. You write standard Python code in the Google ADK to trigger these runs. Gemini handles the transport, making sure your agent can query Mela project costs and format them for your database. No messy custom ETL pipelines required.

Automate dispatching with Gemini

Your Google ADK agent executes `list_teams` and `update_activity_status` to coordinate field crews based on real-time needs. When a Mela task is marked finished, the Gemini agent checks who is free and assigns the next job. It removes the lag between finishing a task and starting the next one. You can restrict which tools are exposed using the `tool_names` filter in the Google ADK. If you only want the agent posting Mela updates, block the status modification tools entirely. It gives you precise control over what the MCP agent can do on site.

Setup guide

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

Initialize `McpToolset` with your HTTP server parameters and pass it to your `LlmAgent`. The ADK handles the connection, exposing tools like `create_activity` to Gemini.

Yes, you can use the `tool_names` filter when setting up your toolset. This lets you limit the agent to harmless tools like `list_activities` while blocking write tools.

The ADK passes outputs from `list_checklists` directly into Gemini's large context window. This allows the model to analyze hundreds of pages of site logs at once without losing track of details.

Yes, because the ADK runs in the Google Cloud ecosystem. You can have your agent fetch data using `get_accounting_data` and write it directly to BigQuery tables.

All communication runs through an isolated V8 sandbox with zero-trust architecture. Your cost records and financial logs are processed in ephemeral environments. No data is stored on our servers after the tool execution completes.

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