How to Use the FRED Series — U.S. Economic Time Series MCP in OpenAI Agents SDK

Q: Can I use FRED Series — U.S. Economic Time Series to pull specific historical revisions in OpenAI Agents SDK?

Yes, you use getvintagedates to find when data points were revised. Your OpenAI Agents SDK agent can then pull the exact values that were public on a specific date, preventing lookahead bias in your backtests.

Q: Does the FRED Series — U.S. Economic Time Series server support unit transformations out of the box for OpenAI Agents SDK?

Yes, the getobservations tool supports units like percent change, log, and change from a year ago. Your OpenAI Agents SDK agent simply passes these parameters during the tool call to get pre-calculated values.

Fetch raw economic metrics directly into your OpenAI Agents SDK production workflows without hardcoding API endpoints.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FRED Series — U.S. Economic Time Series MCP to OpenAI Agents SDK

Create your Vinkius account to connect FRED Series — U.S. Economic Time Series 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 FRED Series — U.S. Economic Time Series with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Economic Queries with OpenAI Agents SDK

The `search_series` tool lets your agent scan over 816,000 U.S. economic data series using simple keyword queries. You get back series IDs, titles, and popularity metrics directly inside your OpenAI Agents SDK runtime using this MCP Server. This means your agent can independently discover the correct data keys for GDP or unemployment without you hardcoding a single identifier. It handles the discovery phase dynamically before pulling the actual numbers.

Fetch and Transform Raw Observations

The `get_observations` tool pulls the actual values for any series ID like CPIAUCSL or UNRATE with built-in frequency aggregation. Your agent can request quarterly averages or annual percent changes directly through the OpenAI Agents SDK stream. By letting the MCP Server handle the heavy math of transformations, your agent receives clean, structured numerical arrays. This keeps your token usage low because you aren't feeding raw, unaggregated daily noise into your LLM context window.

Monitor Vintage Releases and Revisions

The `get_vintage_dates` tool exposes the historical revision history of economic indicators so your agent can track when data was altered. This is critical for backtesting trading models where historical accuracy dictates performance. Combining this with `get_series_updates` allows your OpenAI Agents SDK deployment to poll for newly released macro data. Your system stays updated with the latest releases without manual intervention.

Setup guide

Set up FRED Series — U.S. Economic Time Series 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 FRED Series — U.S. Economic Time Series tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives FRED Series — U.S. Economic Time Series tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate FRED Series — U.S. Economic Time Series 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="FRED Series — U.S. Economic Time Series Agent",
            instructions="You have access to FRED Series — U.S. Economic Time Series 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 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 Series — U.S. Economic Time Series 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 Series — U.S. Economic Time Series MCP in OpenAI Agents SDK

The MCP server passes raw requests directly to the FRED API, which enforces a strict limit of 120 requests per minute. You should configure your OpenAI Agents SDK runner to catch rate-limit errors or implement a basic queue to avoid hitting this ceiling during heavy parallel agent runs.

Yes, you use `get_vintage_dates` to find when data points were revised. Your OpenAI Agents SDK agent can then pull the exact values that were public on a specific date, preventing lookahead bias in your backtests.

Yes, the `get_observations` tool supports units like percent change, log, and change from a year ago. Your OpenAI Agents SDK agent simply passes these parameters during the tool call to get pre-calculated values.

You can write a system prompt in your agent configuration to limit searches. The `search_series` tool itself will search the entire FRED catalog, but your agent will only execute calls on the IDs you permit it to use.

Your FRED API key is stored securely as an environment variable in the Vinkius sandbox and is never exposed to the LLM. Only the raw query parameters and the resulting economic time series data pass between your OpenAI Agents SDK agent and the secure 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