How to Use the FRED Tags & Sources — Data Discovery MCP in Pydantic AI

Q: How do I connect the FRED Tags & Sources — Data Discovery MCP Server to Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your HTTP endpoint and pass it into the toolsets parameter of your Agent constructor.

Q: Why use the unified MCPToolset approach?

The old MCPServerHTTP method is deprecated. MCPToolset provides a cleaner interface for Streamable HTTP transports and handles the schema conversion natively.

Strongly typed macroeconomic data discovery for your Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FRED Tags & Sources — Data Discovery MCP to Pydantic AI

Create your Vinkius account to connect FRED Tags & Sources — Data Discovery 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 FRED Tags & Sources — Data Discovery with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query exact metadata combinations

The `get_series_by_tags` tool executes multi-variable searches against the FRED index. Your agent provides specific inclusion and exclusion strings to isolate the exact dataset. It finds the intersection of "gdp" and "quarterly" while dropping unwanted metrics. Pydantic AI demands strict typing. When the API returns the matching series, the framework validates the response against your predefined models. If the upstream data structure changes, the agent fails loudly rather than passing corrupted series IDs downstream.

Retrieve the official source registry

Triggering the `list_sources` tool returns the complete list of 107 data publishers. Your agent pulls the names and IDs of institutions like the Census Bureau. It uses this list to verify where specific metrics originate. Data pipelines require exact provenance. Your agent checks the source ID before trusting the numbers. You build a Pydantic model for the expected source schema, ensuring every publisher record matches your internal compliance requirements exactly.

Connect this MCP Server to Pydantic AI

The `search_tags` tool allows your agent to find valid taxonomy terms via text search. It returns geographic, topic, and frequency labels. The agent uses this to map user requests to official St. Louis Fed terminology. You integrate this using the unified `MCPToolset` class. Drop the endpoint URL into the constructor and pass it to your Agent. The framework supports Streamable HTTP out of the box, connecting your model to the metadata endpoints without the deprecated `MCPServerHTTP` wrapper.

Setup guide

Set up FRED Tags & Sources — Data Discovery 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": {
        "fred-tags-sources-data-discovery-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to FRED Tags & Sources — Data Discovery tools.",
)

result = await agent.run("List recent FRED Tags & Sources — Data Discovery 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 FRED. 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 FRED Tags & Sources — Data Discovery 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 FRED Tags & Sources — Data Discovery MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your HTTP endpoint and pass it into the `toolsets` parameter of your Agent constructor.

Pydantic AI catches it immediately. The runtime validation throws an error before the agent can hallucinate an answer based on malformed taxonomy data.

Yes. The framework is model-agnostic. As long as your local model supports function calling, it can interact with the `search_tags` and `list_sources` tools perfectly.

The old `MCPServerHTTP` method is deprecated. `MCPToolset` provides a cleaner interface for Streamable HTTP transports and handles the schema conversion natively.

The system retains nothing. You query public macroeconomic labels and source registries through an ephemeral V8 Isolate. Once the Pydantic AI agent receives the payload, the connection terminates and all state is destroyed.

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