How to Use the Forecast MCP in Google ADK

Q: How do I set up Forecast with Google ADK?

Run pip install google-adk. Wrap your endpoint in StreamableHttpServerParameters and pass it to McpToolset. Assign that toolset to your LlmAgent.

Q: Can I restrict which Forecast tools Google ADK exposes?

You can filter them easily. Use the toolnames parameter when defining your toolset to only expose listtasks or listpeople to the agent.

Bring the Forecast MCP Server into Google ADK to analyze tasks and team availability using Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Forecast MCP to Google ADK

Create your Vinkius account to connect Forecast 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 Forecast with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Forecast Projects with Google ADK

The `list_projects` and `get_project` tools feed your entire project portfolio directly into Gemini. Google ADK handles the connection through its `McpToolset` wrapper. Because Gemini holds over a million tokens, you can dump years of historical project data into a single prompt without chunking. The agent reads the project parameters and cross-references them with your existing BigQuery datasets. You get a unified view of your operations. The model spots patterns in project delays by comparing Forecast timelines against your internal data warehouse.

Map Team Availability to Active Tasks

Your enterprise agent checks who is free using `list_people` and assigns them to work found via `list_tasks`. You restrict which tools the agent sees using the `tool_names` filter in Google ADK. This keeps the model focused strictly on resource allocation. Running this on Google Cloud means you can tie these task updates directly into Vertex AI pipelines. The agent reads the task status, processes the text, and triggers downstream cloud functions based on the current workload.

Audit Milestones via MCP Server

Execute `list_milestones` to pull upcoming deadlines and match them against customer records from `list_clients`. The Google ADK framework manages the HTTP transport automatically. Your script just asks for the data and receives it from this MCP Server. You avoid writing custom integration code for Gemini. The `LlmAgent` class accepts the toolset array and maps the Forecast endpoints to native function calls. The model executes the data fetch and returns structured text.

Setup guide

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

Run `pip install google-adk`. Wrap your endpoint in `StreamableHttpServerParameters` and pass it to `McpToolset`. Assign that toolset to your `LlmAgent`.

You can filter them easily. Use the `tool_names` parameter when defining your toolset to only expose `list_tasks` or `list_people` to the agent.

Your agent can read from Forecast and write to BigQuery in the same execution loop. The framework supports passing multiple toolsets to a single Gemini instance.

The framework supports both Stdio and HTTP transports. For Vinkius-hosted endpoints, you will configure the HTTP connection parameters.

This integration accesses client names, milestone dates, and task assignments. Your requests route through a zero-trust ephemeral environment. Authentication requires a single endpoint token, and no client data is cached on our infrastructure.

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