How to Use the GovInfo MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK pipeline search specific GovInfo collections?

Yes. The agent can use listcollections to find the target ID and then run getcollection to pull packages within a specific date range.

Q: How does the agent handle large legislative packages?

The agent uses getpackagesummary to inspect the metadata first. It then decides whether to grab the whole package or split the retrieval using listpackagegranules.

Feed official US government records to your OpenAI Agents SDK pipelines with zero-config MCP Server discovery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GovInfo MCP to OpenAI Agents SDK

Create your Vinkius account to connect GovInfo 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 GovInfo with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct federal archive search in OpenAI Agents SDK

Point your agents directly to the US government library with this MCP Server. By passing the server configuration to your Agent constructor, your agent instantly gains the ability to use `search_documents` to find federal laws and regulations. The agent handles the query construction behind the scenes. It can parse the raw results and immediately pass them to another specialized agent in your SDK pipeline without manual parsing.

Granular document hierarchy mapping

Federal publications are massive, often burying critical clauses deep inside sub-documents. Your agent uses `list_package_granules` and `get_granule_summary` to map out the structure of congressional bills or federal register entries. This targeted access keeps token usage low because the agent only pulls the specific section it needs instead of swallowing a 500-page document. You can trace this exact tool execution in your OpenAI dashboard to see exactly which granule was retrieved.

Automated related document crawls

Tracking regulatory changes requires finding connected files across different dates. Your OpenAI Agents SDK pipeline can use `get_related_documents` and `get_published` to automatically build a timeline of a specific policy's evolution. Because the SDK supports strict guardrails, you can define validation rules that prevent the agent from fetching documents outside a specific date range, keeping your research pipeline on track.

Setup guide

Set up GovInfo 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 GovInfo tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives GovInfo tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate GovInfo 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="GovInfo Agent",
            instructions="You have access to GovInfo 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 GovInfo. 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 GovInfo 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 GovInfo MCP in OpenAI Agents SDK

Install the SDK and use the MCPServerStreamableHttp client to connect to your Vinkius endpoint. Pass the server instance directly into your Agent constructor to let the agent auto-discover the tools.

Yes. The agent can use `list_collections` to find the target ID and then run `get_collection` to pull packages within a specific date range.

Yes. Set cacheToolsList to True in your server parameters to speed up agent initialization times and reduce tool discovery overhead.

The agent uses `get_package_summary` to inspect the metadata first. It then decides whether to grab the whole package or split the retrieval using `list_package_granules`.

All queries hit public federal document repositories, so no classified data is ever touched. Vinkius runs the server in an ephemeral sandbox, ensuring your search terms and API keys never persist on disk.

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