How to Use the Finnhub MCP in Pydantic AI

Q: How do I register the Finnhub toolset in Pydantic AI?

Use the unified MCPToolset class initialized with your Vinkius endpoint URL. Pass this toolset instance inside the toolsets list when configuring your agent.

Q: What happens if a financial metric is missing from a company query?

If getbasicfinancials returns a payload missing a required field, the framework throws a validation error. You can define optional fields using Python's Optional type to handle varying levels of disclosure from different companies.

Ensure absolute type safety for your Finnhub financial data pipelines using the Pydantic AI framework.

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 Pydantic AI

Create your Vinkius account to connect Finnhub to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarantees on stock quotes with Pydantic AI

`get_stock_quote` delivers real-time pricing data that Pydantic AI validates against rigid Python schemas at runtime. If the API returns a missing field or an unexpected null value, the framework raises a validation error immediately. This strict validation prevents your trading logic from executing on corrupt or incomplete market data. You get clean, typed floats for bid-ask spreads and transaction prices every single time using this MCP Server.

Validated corporate financial metrics

`get_basic_financials` and `get_company_profile` feed complex corporate balance sheets into your structured models. The Pydantic AI framework forces the incoming Finnhub data to conform to your exact Pydantic definitions before your agent makes a decision. If a company profile lacks an industry classification, your agent catches the schema mismatch instantly. This guarantees your quantitative analysis models never ingest malformed data that could skew valuation metrics.

Type-safe asset discovery workflows

`search_symbols` and `list_crypto_symbols` return lists of active tickers that are parsed directly into strongly-typed Python lists. Your agent can confidently pass these validated symbols to downstream execution tools without risking runtime type errors. By wrapping the Finnhub MCP Server in a type-safe toolset, you eliminate the risk of model hallucinations. The agent cannot invent tickers because the framework rejects any output that doesn't match the validated symbol schema.

Setup guide

Set up Finnhub MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "finnhub-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Finnhub tools.",
)

result = await agent.run("List recent Finnhub transactions")
print(result.output)

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 Pydantic AI

If Finnhub alters its response payload, Pydantic AI will raise a validation error at runtime. This prevents silent failures, allowing you to update your schemas before corrupt data propagates through your system.

Yes, the framework supports both SSE and streamable HTTP transports. You can connect your type-safe agent to the Finnhub MCP Server hosted on Vinkius using standard connection strings.

Use the unified `MCPToolset` class initialized with your Vinkius endpoint URL. Pass this toolset instance inside the `toolsets` list when configuring your agent.

If `get_basic_financials` returns a payload missing a required field, the framework throws a validation error. You can define optional fields using Python's `Optional` type to handle varying levels of disclosure from different companies.

All financial metrics, quotes, and crypto symbols are retrieved through an encrypted, ephemeral V8 isolate. Vinkius never logs the contents of your API responses, ensuring your proprietary investment research remains private.

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