How to Use the Marketaux MCP in Pydantic AI

Force strict type validation on Marketaux financial data using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marketaux MCP to Pydantic AI

Create your Vinkius account to connect Marketaux 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 Marketaux with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Catch hallucinated tickers immediately

Financial agents die when they hallucinate data. Pydantic AI forces every response from `get_symbols` and `get_entities` into a strict model. If the API returns garbage, the agent crashes loudly. You want that crash. Silent corruption bankrupts trading strategies. This MCP Server integration ensures your agent only processes exact, validated market identifiers.

Type-safe sentiment analysis via MCP Server

Sentiment scores are just numbers until you validate them. Hook up `get_sentiment_analysis` and let Pydantic verify the bounds of every fear and greed metric. If the data structure shifts, your agent halts. You get a clear validation error instead of a rogue agent buying the wrong asset.

Validate global news feeds

News APIs are notoriously inconsistent. Your agent uses `get_latest_news` and `search_news`, and Pydantic AI checks every string, date, and author field before it enters your logic. You can also validate macro conditions using `get_stock_market_status` and `get_indices`. The framework guarantees the payload matches your schema exactly.

Setup guide

Set up Marketaux 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": {
        "marketaux-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Marketaux 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 Marketaux. 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 Marketaux 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 Marketaux MCP in Pydantic AI

Install the slim package with MCP support. Create an MCPToolset pointing to your HTTP endpoint, and pass it into the toolsets array of your Agent.

No. That class is deprecated. Use the unified MCPToolset approach to connect your agent to the Vinkius MCP Server endpoint.

The agent throws a validation error and stops. It refuses to process the data, which protects your downstream trading logic from structural surprises.

Yes. The framework is model-agnostic. You can pipe the output from `get_trending_news` into a local Llama model or send it to Anthropic.

Your endpoint token connects to an isolated, ephemeral sandbox. The moment your agent retrieves stock indices or news articles, the memory state is wiped completely clean.

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