How to Use the GovInfo MCP in LangChain

Q: How do I pass GovInfo search results into a LangChain agent?

Call searchdocuments within your LangChain agent's tool execution block to query GovInfo. The LangChain agent parses the returned GovInfo JSON payload and feeds the matching document IDs directly into your next chain step.

Q: Can LangChain handle large legislative packages from GovInfo?

Yes, your LangChain chain should first call listpackagegranules to break a massive GovInfo federal package down into smaller, digestible sub-documents. This prevents context window limits from blocking your LangChain summarization prompts on large GovInfo files.

Build LangChain reasoning loops that pull and analyze official US federal records directly through the GovInfo MCP Server.

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 LangChain

Create your Vinkius account to connect GovInfo 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 GovInfo with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain federal document discovery in LangChain

The `search_documents` tool connects your LangChain agent directly to the official GovInfo federal publication index. Your LangChain agent immediately inspects congressional bills, federal register notices, and presidential documents retrieved from GovInfo by feeding search results straight into downstream prompt templates. By linking `list_package_granules` right after a GovInfo search, your LangChain workflow extracts sub-sections of massive legislative bills without human intervention. This setup feeds clean, verified GovInfo text directly into your LangChain memory buffers via the MCP protocol.

Trace legislative metadata paths

The `get_package_summary` tool retrieves top-level GovInfo metadata for specific federal packages to feed your LangChain decision nodes. Your LangChain chains use this structured GovInfo data to branch logic based on publication dates, document types, or issuing agencies. Feed this GovInfo metadata directly into `get_related_documents` to trace historical regulatory changes inside your LangChain pipeline. LangSmith tracks every step of this GovInfo document retrieval chain, showing you the exact latency and token usage of each government query.

Verify historical records with LangChain

The `get_collection` tool pulls specific sets of GovInfo documents within targeted date ranges to populate your LangChain vector stores. Your LangChain agent evaluates historical trends by comparing past regulations from GovInfo with current policy drafts. Running `get_published` lets your LangChain chain monitor daily GovInfo updates as they go live. This keeps your LangChain agents grounded in official sources, avoiding hallucinations by relying strictly on verified GovInfo publications.

Setup guide

Set up GovInfo 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 GovInfo 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({
    "govinfo-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 GovInfo 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 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 LangChain

Call `search_documents` within your LangChain agent's tool execution block to query GovInfo. The LangChain agent parses the returned GovInfo JSON payload and feeds the matching document IDs directly into your next chain step.

Yes, your LangChain chain should first call `list_package_granules` to break a massive GovInfo federal package down into smaller, digestible sub-documents. This prevents context window limits from blocking your LangChain summarization prompts on large GovInfo files.

Combine this GovInfo MCP Server with other endpoints using the LangChain `MultiServerMCPClient` class. This lets your LangChain agent query GovInfo federal documents and cross-reference them with external databases in a single run.

LangSmith captures every GovInfo tool call, showing you the exact input parameters sent to `get_package_summary` or `get_collection`. You will see the raw GovInfo API responses and any connection errors directly in your LangChain tracing dashboard.

Vinkius hosts the GovInfo MCP server inside an isolated V8 sandbox, meaning your GovInfo API credentials and the retrieved US government document metadata never touch external servers or the LangChain client itself. All transit between GovInfo and LangChain happens over zero-trust, ephemeral connections.

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