How to Use the FirstPromoter MCP in Google ADK

Q: How do I configure FirstPromoter within Google ADK using an MCP Server?

Run pip install google-adk and set up the McpToolset using your Vinkius HTTP endpoint. Pass the toolset object to your LlmAgent to expose tools like listcampaigns and getcampaignreport to Gemini.

Q: Can a Google ADK agent write back to FirstPromoter?

Yes, your agent can call write-enabled tools like createpromoter and createreward. You can restrict which tools are exposed by passing a toolnames filter array to the McpToolset constructor.

Q: How does Google ADK handle high-volume data from FirstPromoter?

The ADK passes tool outputs from listconversions directly into Gemini's 1M+ token context. This allows the model to process thousands of referral records simultaneously without hitting context limits.

Run long-context affiliate analysis on Google ADK by connecting your Gemini models directly to FirstPromoter.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FirstPromoter MCP to Google ADK

Create your Vinkius account to connect FirstPromoter 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 FirstPromoter with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Google ADK Enterprise Partner Tracking

The FirstPromoter MCP Server hooks directly into your Google ADK pipelines to feed real-time affiliate data into Gemini. Your enterprise agents run `get_promoter_report` and `list_promoters` across massive contexts to detect high-performing partners. Because Gemini supports long-context windows, you can pass thousands of partner profiles retrieved via `list_promoters` in a single prompt. The agent analyzes recruitment trends and identifies top-tier promoters without chunking data.

Unified BigQuery and Affiliate Matching

Match internal customer databases with affiliate conversions using `get_lead` and `list_conversions`. Google ADK agents pull transaction logs from BigQuery and reconcile them against FirstPromoter records in real-time. The agent runs `get_lead` to verify that a specific referral actually converted in your backend database. This prevents payout duplication and flags self-referral fraud before you run your monthly payroll.

Automated Payout Analysis

Monitor your program's financial health by calling `get_payout_stats` and `list_rewards` through your Google ADK agent using this MCP setup. The tool returns granular payout details that Gemini processes to forecast your upcoming affiliate liabilities. The agent formats these financial summaries and writes them directly to Vertex AI pipelines. This gives your finance team instant visibility into affiliate spend without manual export steps.

Setup guide

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

Run `pip install google-adk` and set up the `McpToolset` using your Vinkius HTTP endpoint. Pass the toolset object to your `LlmAgent` to expose tools like `list_campaigns` and `get_campaign_report` to Gemini.

Yes, your agent can call write-enabled tools like `create_promoter` and `create_reward`. You can restrict which tools are exposed by passing a `tool_names` filter array to the `McpToolset` constructor.

The ADK passes tool outputs from `list_conversions` directly into Gemini's 1M+ token context. This allows the model to process thousands of referral records simultaneously without hitting context limits.

Yes, Google ADK allows your agents to query BigQuery tables and then use `create_reward` to issue payouts based on those internal SQL query results in a single execution loop.

Your referral tokens and customer emails remain within Google Cloud's secure perimeter and Vinkius's zero-trust sandbox. The MCP Server acts as an ephemeral proxy, passing credentials securely without persistent storage.

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