How to Use the EODHD Financial MCP in AutoGen

Let your AutoGen agents debate financial strategies and validate conclusions using live market data from EODHD.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EODHD Financial MCP to AutoGen

Create your Vinkius account to connect EODHD Financial to AutoGen 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 EODHD Financial with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enable Multi-Agent Financial Debate

Create a "Trader" agent that uses `get_realtime_price` to propose a trade. At the same time, a "Risk Analyst" agent can challenge that idea by pulling company valuation data from `get_fundamentals`. The agents converse, using data from the tools as evidence. The final action isn't based on one agent's impulse, but on a consensus reached after the agents challenge each other's findings.

Validate Ideas with Historical Data

One agent can propose a strategy based on a recent stock split found with `get_splits`. Another agent in the group can immediately back-test that idea by pulling years of data with `get_eod_data` and `get_historical_splits`. This adversarial process helps catch bad assumptions before they cost you. The agents argue about the interpretation of the data, leading to a more robust conclusion than a single agent could reach alone.

Automate Research with AutoGen Agent Teams

Set up a group of agents to build a complete market report. One agent uses `get_exchange_symbols` to find all tickers for a market, passing the list to a second agent that fetches bulk data with `get_multi_price`. A third agent then summarizes the findings. You're not just calling tools; you're orchestrating a conversation between specialists. Each agent has access to the full EODHD toolset from this MCP server, but you can assign them specific roles in the research process.

Setup guide

Set up EODHD Financial MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes EODHD Financial tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="EODHD Financial_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent EODHD Financial data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="EODHD Financial_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent EODHD Financial data")
    print(result.messages[-1].content)

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 EODHD Financial 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 EODHD Financial 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 EODHD Financial MCP in AutoGen

Each agent in your group chat can be given access to the toolset. One agent might call `get_dividends`, and another can use that output to decide whether to call `get_fundamentals`, all within the same conversation.

Yes, that's a core AutoGen pattern. Give one agent the goal of finding positive signs with `get_realtime_price` and another the goal of finding risks with `get_fundamentals`. AutoGen facilitates the debate between them.

You don't have to manage it manually. You provide the list of tools to the agents, and AutoGen's framework manages the conversation flow, deciding which agent's turn it is to speak or use a tool like `get_eod_data`.

It surfaces blind spots. A single agent might find a positive signal and act on it. An AutoGen group will have another agent challenge that signal, forcing the first to defend its reasoning with more data, which leads to better decisions.

The MCP server processes requests for public financial market data—like prices, dividends, and fundamental metrics. Each request is handled in a stateless, ephemeral Vinkius instance, ensuring your session's queries aren't persisted on the server.

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