How to Use the Finnhub MCP in OpenAI Agents SDK

Q: Can I trace Finnhub tool calls in the OpenAI Agents SDK dashboard?

Yes, every call to getstockquote or getbasicfinancials appears in your run traces. You can inspect the exact payload sent to the Finnhub MCP Server and the raw JSON response returned to your agent.

Q: How do I set up the Finnhub MCP Server with OpenAI Agents SDK?

Install the packages, then initialize the connection using MCPServerStreamableHttp with your Vinkius endpoint. Pass this server instance directly into your agent's constructor to expose all six financial tools instantly.

Q: How does symbol discovery work during a run?

Your agent uses searchsymbols to find the correct ticker when a user mentions a company name. The model matches the query against Finnhub's database and passes the correct symbol to downstream tools like getcompanyprofile.

Build production-grade OpenAI Agents SDK systems that pull real-time Finnhub stock quotes and financials with built-in guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Finnhub to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe real-time pricing for OpenAI Agents SDK

`get_stock_quote` pulls live stock prices directly into your OpenAI Agents SDK execution loop. This tool feeds raw numbers to your agent, which then runs pre-execution checks to verify price thresholds before triggering any trade logic. By avoiding direct execution, your pipeline prevents bad trades if the API hits a rate limit or returns stale numbers. You configure the agent to pass this data to a validation node, securing your workflow using this MCP Server.

Multi-agent financial research workflows

`get_basic_financials` and `get_company_profile` supply the raw balance sheet data and corporate metadata your research agents need to evaluate market positions. Your lead agent can analyze the high-level profile, then hand off the raw metrics to a specialized analyst agent for valuation. The OpenAI dashboard tracks these handoffs in real time. You see exactly which agent called the Finnhub MCP Server and how the valuation logic processed the raw numbers.

News-driven sentiment analysis

`get_market_news` retrieves the latest headlines to let your OpenAI Agents SDK monitor market sentiment. Your agent parses the news text, extracts sentiment scores, and flags sudden shifts in market tone. Combining this with `search_symbols` lets your agent map news events to specific tickers instantly. The system acts on real-time events without human intervention, keeping your portfolio aligned with breaking market shifts.

Setup guide

Set up Finnhub MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Finnhub tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Finnhub tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Finnhub tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Finnhub Agent",
            instructions="You have access to Finnhub tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Implement local caching or rate-limiting middleware before the agent invokes the tool. If Finnhub returns a 429 error, the SDK's built-in error handling will catch it, allowing your agent to retry or hand off the task to a fallback routine.

Yes, every call to `get_stock_quote` or `get_basic_financials` appears in your run traces. You can inspect the exact payload sent to the Finnhub MCP Server and the raw JSON response returned to your agent.

Install the packages, then initialize the connection using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this server instance directly into your agent's constructor to expose all six financial tools instantly.

Your agent uses `search_symbols` to find the correct ticker when a user mentions a company name. The model matches the query against Finnhub's database and passes the correct symbol to downstream tools like `get_company_profile`.

Vinkius processes your stock tickers and company queries inside an isolated, zero-trust V8 sandbox. Your API keys and financial search parameters never persist on disk, and the ephemeral container destroys your session data immediately after the tool run finishes.

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