How to Use the Harmonic MCP in Google ADK

Q: How do I connect Harmonic to my Google ADK agent to search for investors?

You'll use the McpToolset and provide your Vinkius server URL. Pass this toolset to your LlmAgent constructor. Your agent can then call tools like searchinvestors directly.

Q: Can I limit which Harmonic tools my Google ADK agent can use?

Yes, you can. When you create the McpToolset, you can pass an optional toolnames filter. This lets you expose only specific tools, like enrichcompany, while hiding others from the agent.

Q: How does my agent get info about its own API usage?

There's a simple tool for that. Have your agent call getapiprofile. It returns information about the current API user and usage stats, which is useful for monitoring and debugging.

Connect your Google ADK agent to live startup intelligence from Harmonic. Turn your BigQuery data into actionable insights.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Harmonic MCP to Google ADK

Create your Vinkius account to connect Harmonic 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 Harmonic with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enrich Your BigQuery Data

The `enrich_company` tool is designed for this. If you have a table of company domains in BigQuery, your Google ADK agent can read it, then call Harmonic to fill in the blanks. It can pull firmographics, tech stack, and headcount data for each one. Your Gemini-powered agent can then take that enriched data and push it back to a new table in BigQuery. This creates a powerful, automated loop for keeping your internal company database up to date without any manual data entry.

Enterprise-Scale Discovery

The `search_startups` tool lets your agent comb through the market for companies that fit your investment thesis. You can filter by industry, size, and location. For mapping out an ecosystem, the `get_investor_portfolio` tool shows you every company a specific firm has backed. Because this is running on Google Cloud, you can run these jobs at scale. A Google ADK agent can perform wide-ranging searches, aggregate the results, and drop them into a report or a new cloud database, all within your existing infrastructure.

Long-Context Analysis with Google ADK

Use the `list_funding_rounds` and `list_company_news` tools to pull a company's complete history. A Gemini agent, with its huge context window, can hold all of this data in memory at once. This is a real advantage. Instead of just getting facts, you can ask the agent for a summary of the company's trajectory, its funding velocity, or any red flags in its history. The agent has all the raw data from this MCP server to give you a detailed and accurate analysis.

Setup guide

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

You'll use the `McpToolset` and provide your Vinkius server URL. Pass this toolset to your `LlmAgent` constructor. Your agent can then call tools like `search_investors` directly.

Yes, you can. When you create the `McpToolset`, you can pass an optional `tool_names` filter. This lets you expose only specific tools, like `enrich_company`, while hiding others from the agent.

That's a primary use case. Your agent can use Harmonic tools like `search_startups` to find data, then use native Google Cloud tools to write those results directly into a BigQuery table for analysis.

There's a simple tool for that. Have your agent call `get_api_profile`. It returns information about the current API user and usage stats, which is useful for monitoring and debugging.

The server processes business data like company firmographics and public funding rounds. Vinkius security is built on V8 Isolate sandboxes. This means each request your agent makes runs in its own secure, separate environment, preventing any data cross-contamination.

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