How to Use the DISCO MCP in LangChain

LangChain agents chain live DISCO matter data and document metadata into multi-step legal discovery pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DISCO MCP to LangChain

Create your Vinkius account to connect DISCO 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 DISCO with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Link DISCO searches directly to downstream analysis

LangChain agents feed the output of `search_matter_documents` directly into subsequent validation chains. Instead of copying search results manually, your agent grabs the exact matching records and immediately runs them through your custom evaluation prompts. This chaining mechanism makes it easy to run multi-step legal reviews. The agent checks `list_document_tags` to classify files, then passes those filtered IDs to `get_document_metadata` to verify file types before your pipeline processes them.

Trace every DISCO MCP Server tool call with LangSmith

Debugging complex litigation searches requires absolute visibility. This MCP Server exposes raw tool execution details so you can monitor latency and token costs for every call to `list_matter_documents` inside your LangSmith dashboard. You see the exact parameters passed to `get_matter_details` and can verify if the agent is hallucinating matter IDs. No more guessing why a document search failed; the entire execution path is logged and visible.

Build autonomous ReAct agents for legal ops

LangChain lets you deploy agents that decide which tool to call next based on what they find. If the agent runs `list_recently_ingested_documents` and finds new files, it can dynamically decide to trigger `list_matter_access_users` to verify who has access to them. This autonomous decision loop reduces the code you need to write. The agent handles the conditional logic of navigating legal matters, keeping your litigation pipelines moving without manual intervention.

Setup guide

Set up DISCO 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 DISCO 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({
    "disco-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 DISCO 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 DISCO. 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 DISCO 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 DISCO MCP in LangChain

LangChain handles rate limits by using standard retry mechanisms in your chain configuration. When calling `search_matter_documents` or `list_matter_documents`, the MCP server passes the raw API responses, letting your LangChain runnables back off and retry automatically.

Yes, every tool call is fully visible in LangSmith. When your agent calls `get_document_metadata` or `list_document_tags`, LangSmith captures the exact inputs, outputs, and latency of that specific MCP step.

You map the matter IDs as inputs to your chain, and the agent uses `get_matter_details` to verify each one. The agent can then loop through the list, calling `list_matter_documents` for each validated ID in a single run.

You configure your Vinkius connection token when initializing the MultiServerMCPClient. The server manages the underlying API credentials securely, so your agent only needs to request tools like `list_legal_matters`.

Your legal documents, matter metadata, and user access lists stay strictly within the Vinkius V8 sandbox and your local memory. The MCP server processes calls to `list_matter_access_users` and `get_document_metadata` using ephemeral instances that never cache or store your sensitive litigation data.

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