How to Use the CB Insights MCP in Google ADK

Q: How do I integrate CB Insights data into BigQuery using Google ADK?

First, use the McpToolset to give your Google ADK agent access to CB Insights tools like getdeal. Then, your agent can call those tools and use a native BigQuery tool to write the results directly into your tables. The agent acts as the bridge.

Q: Does the Google ADK support filtering which CB Insights tools my agent can use?

Yes. When you configure the McpToolset for CB Insights, you can pass a toolnames list. This restricts the agent to only the specified tools, which is useful for building specialized, single-purpose agents.

Connect Google ADK agents to CB Insights for market intelligence that feeds directly into your BigQuery tables and Vertex AI pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CB Insights MCP to Google ADK

Create your Vinkius account to connect CB Insights 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 CB Insights with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Market Trends with Gemini

Feed your Gemini-powered agent a massive list of companies using `list_organizations`. Then, have it loop through and pull detailed funding histories with `get_org_funding`. Gemini's long-context window lets it analyze the results in a single pass. You can build agents that pull raw data from this MCP Server and then use native Google ADK tools to write it directly into BigQuery. It's a straight line from market signal to your enterprise data warehouse.

Connect CB Insights to Your Google ADK Agent

Use the `McpToolset` to give your LlmAgent access to the CB Insights tools. It can then use operations like `list_industries`, `list_investors`, and `get_investor_portfolio` to gather the raw data for an investment thesis. Your agent can hold the context of hundreds of deals and investor profiles at once. This lets you ask complex questions that require synthesizing information across the entire CB Insights dataset, not just one-off lookups.

Filter and Focus Your Agent

The `check_cbi_status` tool is a simple way to confirm connectivity before running a long job. It’s good practice for agents running in a CI/CD pipeline. When you initialize the `McpToolset`, you can use the `tool_names` filter. This lets you create specialized agents that only have access to specific tools, like a 'deal-finder' agent that can only use `list_deals_by_org`. This is a simple way to add a layer of control for your enterprise agents.

Setup guide

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

First, use the `McpToolset` to give your Google ADK agent access to CB Insights tools like `get_deal`. Then, your agent can call those tools and use a native BigQuery tool to write the results directly into your tables. The agent acts as the bridge.

Absolutely. The Google ADK is designed for Gemini. You can use its long-context capabilities to have an agent analyze large amounts of market data from the CB Insights MCP Server in one shot.

Yes. When you configure the `McpToolset` for CB Insights, you can pass a `tool_names` list. This restricts the agent to only the specified tools, which is useful for building specialized, single-purpose agents.

No. This is a managed MCP server that provides a standardized tool interface for your AI agent. It still uses your CB Insights API credentials to fetch data on your behalf.

Your agent authenticates with a single Vinkius token. Requests for your CB Insights investor and portfolio data are passed through a zero-trust, ephemeral V8 isolate sandbox on their way to the API. No sensitive data is logged or stored by the Vinkius platform.

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