How to Use the EOD Historical Data MCP in Google ADK

Q: How do I make an agent use the EOD Historical Data MCP server with Google ADK?

After you pip install google-adk, create an McpToolset instance pointing to your Vinkius server URL. You then pass this toolset into the tools list when initializing your LlmAgent.

Q: Can a Google ADK agent use EOD Historical Data to find new IPOs?

Yes, the agent can call the getcalendaripos tool. It gets a list of upcoming initial public offerings, which you can then process or store in a Google Sheet or BigQuery table.

Q: What's the best way to get historical prices for backtesting with Google ADK and EOD Historical Data?

Use the geteodhistorical tool for daily data or getintradayhistorical for minute-by-minute data. Your agent can fetch the data and load it into a Pandas DataFrame or a cloud database for your backtesting engine to use.

Q: Can I resolve a CUSIP to a ticker symbol?

You can. The getidmapping tool is designed for exactly this. Your agent can take an identifier like a CUSIP or ISIN and find the corresponding stock ticker that the other tools recognize.

Connect Gemini agents to global financial markets with Google ADK and EOD Historical Data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EOD Historical Data MCP to Google ADK

Create your Vinkius account to connect EOD Historical Data 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 EOD Historical Data with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Market Data in BigQuery

The `get_bulk_fundamentals` tool is built for this workflow. Have your Google ADK agent pull fundamental data for an entire exchange—like the NYSE—and write it directly to a BigQuery table. This creates a solid dataset for large-scale analysis inside your Google Cloud project. There's no need to build a separate ETL pipeline; the agent acts as the bridge. Use Gemini's long-context window to reason over the results and plan next steps, like joining the fundamentals data with historical prices from `get_eod_historical`.

Your Google ADK Agent as a Quant

This MCP Server turns your agent into a quantitative analyst. It can use tools like `get_technical_indicators` to calculate SMAs and RSIs, or `get_commodities` to track oil and gold prices alongside equities. The `McpToolset` makes it simple to add all 26 EOD Historical Data tools to your `LlmAgent`. You can also filter the `tool_names` to create specialized agents—one for macro data using `get_ust_yield_rates` and another for company-specific news with `get_news`.

Build Enterprise Financial Bots

Go beyond simple queries. Use Google ADK to build agents that perform multi-step financial research. For instance, an agent can use `search_assets` to find a company, `get_fundamentals` to check its health, and `get_calendar_earnings` to see when its next report is due. Because you're in the Google ecosystem, you can trigger these agents from Cloud Functions or schedule them with Cloud Scheduler. It's a solid foundation for building automated, enterprise-grade financial monitoring systems.

Setup guide

Set up EOD Historical Data 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 EOD Historical Data 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="EOD Historical Data_agent",
    model="gemini-2.0-flash",
    instruction="You have access to EOD Historical Data 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 EOD Historical Data. 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 EOD Historical Data 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 EOD Historical Data MCP in Google ADK

After you `pip install google-adk`, create an `McpToolset` instance pointing to your Vinkius server URL. You then pass this toolset into the `tools` list when initializing your `LlmAgent`.

Yes, the agent can call the `get_calendar_ipos` tool. It gets a list of upcoming initial public offerings, which you can then process or store in a Google Sheet or BigQuery table.

Use the `get_eod_historical` tool for daily data or `get_intraday_historical` for minute-by-minute data. Your agent can fetch the data and load it into a Pandas DataFrame or a cloud database for your backtesting engine to use.

You can. The `get_id_mapping` tool is designed for exactly this. Your agent can take an identifier like a CUSIP or ISIN and find the corresponding stock ticker that the other tools recognize.

The connection between your agent and the MCP server is encrypted. Vinkius processes your requests for market data, such as historical prices or earnings calendars, in an isolated environment that's destroyed after each session. No query data is persisted on 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