How to Use the Library of Congress MCP in LangChain

Q: How do I chain a Library of Congress search to OCR extraction in LangChain?

Use the search tool to find relevant historical documents, then pass the item identifiers to gettextservice in your chain. LangChain handles this output-to-input handoff automatically within a single agent execution loop.

Q: Can I trace Library of Congress tool latency using LangChain and LangSmith?

Yes, every call to tools like getitem or listcollections is recorded in LangSmith. You can view the exact JSON payloads, token counts, and execution times for each historical query.

Q: What is the best way to handle paginated collections in LangChain?

Your agent should call getcollectionitems iteratively. You can write a short loop in your LangGraph chain that checks the returned item list and requests the next page until all records are retrieved.

Build LangChain agents that crawl Library of Congress archives, chaining raw searches directly into deep OCR text analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Library of Congress MCP to LangChain

Create your Vinkius account to connect Library of 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 Library of Congress with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain OCR extraction to raw search queries

The `search` tool lets your LangChain agent query millions of historical records, passing the resulting document IDs directly into the next link of your chain. Your ReAct agent analyzes the raw search results, isolates the most relevant historical manuscripts, and immediately feeds those IDs to other tools without manual coding. By feeding these identifiers directly into `get_text_service`, your chain extracts raw OCR text and word coordinates in a single run. You observe the exact data flow and latency of these multi-step historical queries inside your LangSmith dashboard.

Multi-step media metadata pipelines

The `search_format` tool targets specific archival medium types like maps or audio, giving your LangChain agent a structured starting point. The agent filters the massive catalog by format, then passes the discovered resource IDs to downstream tasks. Your agent then calls `get_image_info` to retrieve IIIF technical metadata for high-resolution maps. This MCP Server lets you combine these media-specific steps into a single LangChain runnable that runs sequentially.

Resolve deep bibliographic records

The `get_item` tool retrieves deep bibliographic details for any single archive record your agent encounters. When your agent finds a citation, it calls this tool to pull down publisher data, creation dates, and physical descriptions. If the item contains digitized files, the agent grabs the exact assets using `get_resource`. This MCP integration gives your LangChain pipelines direct access to the world's largest physical and digital repository.

Setup guide

Set up Library of 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 Library of 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({
    "library-of-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 Library of 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 Library of Congress. 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 Library of 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 Library of Congress MCP in LangChain

Use the `search` tool to find relevant historical documents, then pass the item identifiers to `get_text_service` in your chain. LangChain handles this output-to-input handoff automatically within a single agent execution loop.

Yes, every call to tools like `get_item` or `list_collections` is recorded in LangSmith. You can view the exact JSON payloads, token counts, and execution times for each historical query.

You initialize the MultiServerMCPClient with the Library of Congress endpoint alongside your other servers. LangChain aggregates all tools, allowing your agent to query historical records and save them to a database in one run.

Your agent should call `get_collection_items` iteratively. You can write a short loop in your LangGraph chain that checks the returned item list and requests the next page until all records are retrieved.

This server only accesses public Library of Congress bibliographic records, OCR text, and image metadata. All requests are routed through a secure, ephemeral V8 isolate sandbox on Vinkius, ensuring your LangChain environment remains isolated and no search history is stored.

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