How to Use the FRED Full Access — U.S. Economic Intelligence MCP in AutoGen

Q: How do I load FRED Full Access — U.S. Economic Intelligence into AutoGen?

Install autogen-extmcp. Configure StreamableHttpServerParams with the server URL, then pass the tools directly to your AssistantAgent constructor.

Q: Do the agents know how to format the time series data?

The McpToolAdapter automatically converts the JSON schemas. The agents understand they can request percentage changes or logarithmic transformations directly from the API.

Q: How do agents handle the 816,000 available series?

They use searchseries and searchtags to narrow the field. They debate the relevance of the search results before committing to pulling massive observation datasets.

Equip your AutoGen multi-agent debates with hard Federal Reserve data to force consensus on macroeconomic trends.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FRED Full Access — U.S. Economic Intelligence MCP to AutoGen

Create your Vinkius account to connect FRED Full Access — U.S. Economic Intelligence to AutoGen 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 Full Access — U.S. Economic Intelligence with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Data-Driven Agent Negotiation

The `get_release_series` tool feeds raw employment or inflation numbers into your AutoGen MCP conversation environment. A data-gathering agent pulls the latest non-farm payrolls, while an analytical agent immediately challenges the figures by requesting historical revisions. They negotiate the interpretation. The first agent uses `get_vintage_dates` to prove what the market knew at the time, forcing the analytical agent to adjust its backtesting model based on the actual historical release schedule.

AutoGen MCP Server Integration

The `get_category_series` tool lets your agents systematically explore entirely new economic sectors without human intervention. One agent maps the root categories via `get_category_children`, while another filters the resulting series by frequency and units. This creates an autonomous discovery loop. The agents debate which indicators matter most for a specific industry, pull the data via `get_observations`, and formulate a joint macroeconomic forecast.

Geographic Contagion Analysis

The `get_geo_shapes` tool provides the geographic boundaries needed for spatial economic debates. Your agents pull county or MSA-level shapefiles and match them against cross-sectional data from `get_regional_data`. A risk agent might argue that regional banking stress is isolated, while a macro agent pulls broader state-level data to prove contagion. They argue the data points until they reach a mathematically sound conclusion.

Setup guide

Set up FRED Full Access — U.S. Economic Intelligence MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes FRED Full Access — U.S. Economic Intelligence tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="FRED Full Access — U.S. Economic Intelligence_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent FRED Full Access — U.S. Economic Intelligence data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="FRED Full Access — U.S. Economic Intelligence_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent FRED Full Access — U.S. Economic Intelligence data")
    print(result.messages[-1].content)

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 Full Access — U.S. Economic Intelligence 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 Full Access — U.S. Economic Intelligence MCP in AutoGen

Install `autogen-ext[mcp]`. Configure `StreamableHttpServerParams` with the server URL, then pass the tools directly to your `AssistantAgent` constructor.

Yes. Any agent holding the tools in its configuration can query the Federal Reserve data. They share the results in the conversation history.

The `McpToolAdapter` automatically converts the JSON schemas. The agents understand they can request percentage changes or logarithmic transformations directly from the API.

They use `search_series` and `search_tags` to narrow the field. They debate the relevance of the search results before committing to pulling massive observation datasets.

The MCP server executes read-only queries against Federal Reserve category tags, series metadata, and observation values. Your agents' internal debates, prompts, and negotiation logic stay entirely within your local memory space.

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