How to Use the U.S. Congress MCP in AutoGen

Q: If I need historical data from U.S. Congress, how does AutoGen help?

You can assign one agent to pull sessions using listcongresssessions and another agent to check if specific bills were active during those periods. The negotiation reveals the most relevant overlaps.

Get debated legislative conclusions with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect U.S. Congress MCP to AutoGen

Create your Vinkius account to connect U.S. Congress 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 U.S. Congress with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Reviewing Bill Scope and Impact

You've got a bill from `list_congress_bills`. Give that to Agent A. Then, assign Agent B the task of checking related amendments using `list_congress_amendments`. These two agents will debate whether the bill's scope is fully covered by its current amendments. The system converges on a decision: Is there a gap? The answer isn't just data; it's a consensus derived from competing perspectives.

Cross-Referencing Members and Treaties

Agent A gets the list of treaties via `list_congress_treaties`. Agent B then checks which key members, retrieved using `list_congress_members`, were involved in passing those treaties. They argue over potential political friction points. The final output is a negotiated report that flags conflicts or gaps, rather than just listing connections.

Analyzing Committee Oversight

You can set up agents to review committee oversight. Agent A pulls all committees using `list_congress_committees`. Agent B then checks if those listed committees have overlapping jurisdictions with any given bill details from `get_bill_details`. The debate resolves into a clear risk assessment: Which committees need to be involved next, and why?

Setup guide

Set up U.S. Congress 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 U.S. Congress 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="U.S. Congress_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent U.S. Congress 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="U.S. Congress_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent U.S. Congress 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 Congress.gov. 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 U.S. Congress 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 U.S. Congress MCP in AutoGen

It uses multiple agents that talk to each other. Instead of giving you a single answer, it forces the agents to debate the findings, leading to a more robust, vetted conclusion about the legislative topic.

Yes. You can set up one agent to list all nominations and another agent to critique them based on criteria like tenure or jurisdiction, leading to a negotiated summary of the gaps.

You can assign one agent to pull sessions using `list_congress_sessions` and another agent to check if specific bills were active during those periods. The negotiation reveals the most relevant overlaps.

The core function is validation through debate. If one agent presents a finding, another can challenge it with data from a different tool call (like comparing committee lists to bill details).

You'll get structured reports detailing the findings from multiple agents, rather than raw data dumps. These reports include flagged risks and consensus conclusions based on the competing inputs.

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