How to Use the Finnhub MCP in Google ADK

Q: Can I filter which Finnhub tools are exposed to my Google ADK agent?

Yes, you can use the toolnames filter in the McpToolset configuration to restrict access. For instance, you can expose only getstockquote while keeping the fundamental analysis tools hidden.

Q: How do I pull company profiles into Vertex AI?

Your agent invokes getcompanyprofile to fetch corporate metadata, which is then passed to Vertex AI models for entity extraction. This keeps your machine learning pipelines supplied with clean, structured corporate profiles.

Feed live Finnhub market data directly into your Google ADK pipelines to analyze millions of tokens of financial context.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Finnhub MCP to Google ADK

Create your Vinkius account to connect Finnhub 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 Finnhub with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deep market research via Google ADK

`get_basic_financials` feeds historical metrics directly into your Gemini long-context window. Because this MCP Server supports massive token limits, your agent can ingest years of Finnhub financial data at once to spot long-term valuation trends. This setup avoids the need to chunk financial reports. The model processes the entire raw dataset in a single pass, ensuring no critical balance sheet metrics are lost in translation.

Connecting live quotes to enterprise data warehouse

`get_stock_quote` pulls real-time pricing data that your Google ADK agent can compare against historical tables stored in BigQuery. The agent queries your warehouse, retrieves past performance, and uses the live quote to calculate real-time drift. This bridge makes it easy to run regression models on your cloud infrastructure. Your agent executes the Finnhub MCP Server tool, runs the SQL query, and outputs the final risk assessment.

Cross-asset discovery for enterprise pipelines

`list_crypto_symbols` and `search_symbols` allow your Google ADK agent to map out investment universes across both equity and digital asset markets. The agent builds dynamic asset lists on the fly, matching user requests to supported exchange symbols. Once the symbols are resolved, the agent passes them to `get_company_profile` to extract corporate details. Wrapping this MCP Server in your asset discovery pipeline ensures your enterprise workflows always use valid, active tickers before running complex analytical models.

Setup guide

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

Yes, you can use the `tool_names` filter in the `McpToolset` configuration to restrict access. For instance, you can expose only `get_stock_quote` while keeping the fundamental analysis tools hidden.

The framework uses streamable HTTP transports to handle large payloads efficiently. Your Gemini models can ingest massive news batches from `get_market_news` without memory bottlenecks or latency spikes.

Yes, the toolkit supports both Stdio and HTTP transports. You can run the Finnhub MCP Server locally for testing or connect to Vinkius via HTTP for cloud deployments.

Your agent invokes `get_company_profile` to fetch corporate metadata, which is then passed to Vertex AI models for entity extraction. This keeps your machine learning pipelines supplied with clean, structured corporate profiles.

Your stock symbols and financial queries are processed in an ephemeral sandbox that complies with enterprise data standards. No query history or API keys are stored outside the secure session runtime, isolating your proprietary research.

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