How to Use the CourtListener MCP in LangChain

Q: How do I connect CourtListener to LangChain?

Install the langchain-mcp-adapters package. Pass your Vinkius endpoint URL into MultiServerMCPClient and hand those tools directly to your agent.

Q: How do I keep session context between docket searches?

Call client.session() on your MCP client. This keeps the state persistent so your agent remembers previous docket numbers across multiple turns.

Build multi-step legal research pipelines by connecting LangChain agents directly to CourtListener dockets and opinions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CourtListener MCP to LangChain

Create your Vinkius account to connect CourtListener 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 CourtListener with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LangChain MCP Server for Legal Precedent

Chain `search_opinions` directly into `list_citations` to build automated research workflows. ReAct agents look at the text of a ruling and decide on their own which cited cases to pull next. LangSmith tracing gives you full visibility into the process. You see exactly which citations the agent grabbed and how many tokens it burned reading the legal text.

Connect Docket Searches to Judge Profiles

Feed `search_dockets` output straight into `get_judge`. Your agent reads the docket, extracts the presiding judge's name, and pulls their background without you typing a single query. Add `list_financial_disclosures` to that same chain. Now your application automatically flags potential conflicts of interest before you even open the case file.

Aggregate Jurisdictions Automatically

Agents use `list_courts` to map out jurisdictions before running `list_opinions`. They filter down to specific circuits based on intermediate results, requiring zero human intervention. Because this runs through the MultiServerMCPClient, you mix these legal endpoints with your internal database tools. One prompt triggers a full cross-reference across public court records and your firm's private notes.

Setup guide

Set up CourtListener 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 CourtListener 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({
    "courtlistener-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 CourtListener 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 CourtListener. 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 CourtListener 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 CourtListener MCP in LangChain

Install the `langchain-mcp-adapters` package. Pass your Vinkius endpoint URL into `MultiServerMCPClient` and hand those tools directly to your agent.

LangSmith automatically traces every call to this MCP Server. You see the exact latency and token consumption for endpoints like `get_opinion`.

They work perfectly together. The agent reviews the text from `search_opinions` and decides independently to call `list_citations` for further context.

Call `client.session()` on your MCP client. This keeps the state persistent so your agent remembers previous docket numbers across multiple turns.

Vinkius routes your queries through a zero-trust V8 Isolate sandbox. We never store the judge profiles, financial disclosures, or case citations you pull. Your prompts stay between your machine and the remote endpoint.

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