How to Use the DISCO MCP in LlamaIndex

Q: Can I use LlamaIndex to build a RAG pipeline over DISCO document tags?

Yes, you can index tags directly. LlamaIndex queries listdocumenttags to fetch all active categorizations in a matter and stores them as metadata in your vector index, making your document retrieval highly precise.

Q: How does LlamaIndex prevent hallucinations when searching DISCO matters?

LlamaIndex grounds its responses by querying searchmatterdocuments first. The search results are injected directly into the LLM's prompt context as the sole source of truth, preventing the model from inventing non-existent legal evidence.

Q: Can LlamaIndex index user access lists from DISCO?

Yes, LlamaIndex can query listmatteraccessusers and index the resulting user profiles. This allows you to build compliance query engines that verify who has active permissions on sensitive litigation matters.

LlamaIndex indexes DISCO legal documents and matter metadata to power grounded, hallucination-free legal RAG.

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 LlamaIndex

Create your Vinkius account to connect DISCO to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live DISCO MCP Server data directly into vector stores

LlamaIndex doesn't just display search results; it indexes them. When your agent runs `list_matter_documents` through this MCP server, LlamaIndex grabs the document metadata and converts it into searchable nodes in your vector database. This means you can query past litigation files and get answers grounded in actual API data. The agent pulls live records using `get_document_metadata` and immediately updates your index, ensuring your legal RAG pipeline never relies on stale information.

Ground legal QA in actual matter metadata

Stop worrying about your agent inventing legal facts. By calling `get_matter_details` and `list_document_tags`, LlamaIndex builds a structured context layer that forces the LLM to cite real files and tags. When a user asks about case progress, the agent queries `list_recently_ingested_documents` to find new evidence. LlamaIndex uses this raw data to construct its response, preventing the model from hallucinating documents that don't exist.

Build query engines for user access and permissions

Use LlamaIndex to build structured query engines over your litigation team permissions. The agent can pull user lists via `list_authorized_users` and `list_matter_access_users` to build an in-memory index of who has access to what. This lets compliance officers query the index using natural language. They can ask which external counsel can view a specific matter, and the engine answers by cross-referencing the indexed output of those specific tools.

Setup guide

Set up DISCO MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all DISCO MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to DISCO tools.",
)
response = await agent.run("List recent DISCO data")

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 LlamaIndex

Yes, you can index tags directly. LlamaIndex queries `list_document_tags` to fetch all active categorizations in a matter and stores them as metadata in your vector index, making your document retrieval highly precise.

LlamaIndex grounds its responses by querying `search_matter_documents` first. The search results are injected directly into the LLM's prompt context as the sole source of truth, preventing the model from inventing non-existent legal evidence.

Yes, LlamaIndex can query `list_matter_access_users` and index the resulting user profiles. This allows you to build compliance query engines that verify who has active permissions on sensitive litigation matters.

Install llama-index-tools-mcp and initialize the basic client with your Vinkius endpoint. Pass the client to McpToolSpec to load tools like `list_legal_matters` directly into your agent's toolbelt.

Your matter details, document metadata, and tag lists are processed in memory and only sent to your specified vector store. The MCP server handles calls to `get_disco_account_metadata` and `get_matter_details` through a secure, zero-trust sandbox that never retains or logs your confidential legal 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