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

Q: How can I find historical legislative records about U.S. Congress using LangChain?

You use the listcongresssessions tool first to pinpoint the exact dates of the session you need. Then, your agent can combine that time context with other data sources like bill details or committee lists.

Q: Does LangChain help track nominations for U.S. Congress members?

Yes. You run listcongressnominations to pull the records on executive and judicial appointments. The agent can then process these raw nomination lists to flag potential conflicts or gaps in coverage.

Q: If I need historical data on U.S. Congress, how do I use LangChain?

You start by identifying the time frame using listcongresssessions. From there, you can systematically query related records like treaties or bills that were active during those specific sessions.

Build multi-step legislative queries with LangChain.

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 LangChain

Create your Vinkius account to connect U.S. Congress to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Tracking Bill Evolution

Need to see how a bill changed? Start by calling `list_congress_bills` to find the core legislation. Then, chain that result into `get_bill_details`, and finally run those details through `list_congress_amendments`. This sequence shows you the entire life cycle of the law. This process lets your agent decide exactly which tool to fire next based on the data it just pulled. You build a multi-step reasoning pipeline where every output fuels the input for the next step.

Mapping Congressional Players

Want to know who handled what? First, use `list_congress_committees` to get a list of relevant groups. You can then pass those committee names into `list_congress_members` to identify the specific people involved. The agent handles this flow automatically. It moves from high-level group data down to individual members without you having to write multiple API calls. This is pure, executable reasoning.

Analyzing Historical Sessions

Don't just check the current Congress; look back. Start by calling `list_congress_sessions` and specify a historical number, like the 117th session. This gives you the dates. Next, use those date ranges to query other data points, maybe checking for treaties using `list_congress_treaties`. You're linking time periods to specific actions, giving deep context your agent processes step by step.

Setup guide

Set up U.S. Congress MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes U.S. Congress tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "us-congress-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent U.S. Congress transactions"
    })
    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 LangChain

You use the `list_congress_sessions` tool first to pinpoint the exact dates of the session you need. Then, your agent can combine that time context with other data sources like bill details or committee lists.

Yes. You run `list_congress_nominations` to pull the records on executive and judicial appointments. The agent can then process these raw nomination lists to flag potential conflicts or gaps in coverage.

Absolutely. You start by listing all relevant committees using `list_congress_committees`. The agent can then use those committee names as parameters when querying bill details or member lists, narrowing your search fast.

LangChain uses an agent to decide the optimal sequence of tool calls. It's not just running tools in parallel; it passes the output of one function directly as input parameters for the next, creating a logical chain.

You start by identifying the time frame using `list_congress_sessions`. From there, you can systematically query related records like treaties or bills that were active during those specific sessions.

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