How to Use the Docket Alarm MCP in LlamaIndex

Q: How do I index Docket Alarm search results into a LlamaIndex vector store?

You run a search using search or searchdirect and pass the returned court documents to your LlamaIndex document ingest pipeline. The pipeline splits, embeds, and loads the text into your vector store automatically.

Q: Can I use LlamaIndex to query historical Docket Alarm cases offline?

Yes, once you retrieve cases using getdocket or getcomplaintsummary, they are indexed locally. You can query that local vector store without making repeated API calls or incurring extra court fees.

Q: How does LlamaIndex handle the natural language tool askdocket?

The askdocket tool uses Docket Alarm's internal VIDA AI to query specific cases. LlamaIndex can call this tool directly to get synthesized legal answers before deciding to pull the full docket text.

Q: What is the best way to handle state court searches with this tool spec?

Use listsearchdirectcourts to find out which state courts are supported, then run searchdirect to pull the records. The resulting documents are then ready for indexing and retrieval.

Index 732 million legal records directly into your LlamaIndex vector stores for hallucination-free legal RAG with this 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 Docket Alarm MCP to LlamaIndex

Create your Vinkius account to connect Docket Alarm 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 Docket Alarm with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing live court dockets for legal RAG with this MCP Server

Running `get_docket` lets your LlamaIndex pipeline pull live court records and index the raw text directly into your local vector database. This MCP Server lets you ground your legal queries in actual filings rather than training data. When you query your index, the answers are accurate and current. You can retrieve real-time updates from state and federal jurisdictions and instantly make them searchable for your legal team.

Automated judgment extraction and semantic indexing

Executing `extract_judgment` on retrieved files lets your agent pull out the exact rulings and store them as structured metadata in your index. This setup lets you build a searchable database of case outcomes without manual data entry. This lets you run semantic searches over historical cases to find winning arguments. You can compare judges, jurisdictions, and specific outcomes without manually reading thousands of pages.

Natural language querying of Docket Alarm databases

Using `smart_search` turns plain English questions into structured queries that run against Docket Alarm's index. This MCP Server uses natural language instructions to locate relevant litigation files. The retrieved documents are fed directly into your LlamaIndex query engine. This setup bridges the gap between messy court databases and clean, natural language answers.

Setup guide

Set up Docket Alarm 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 Docket Alarm 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 Docket Alarm tools.",
)
response = await agent.run("List recent Docket Alarm 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 Docket Alarm. 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 Docket Alarm 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 Docket Alarm MCP in LlamaIndex

You run a search using `search` or `search_direct` and pass the returned court documents to your LlamaIndex document ingest pipeline. The pipeline splits, embeds, and loads the text into your vector store automatically.

Yes, once you retrieve cases using `get_docket` or `get_complaint_summary`, they are indexed locally. You can query that local vector store without making repeated API calls or incurring extra court fees.

The `ask_docket` tool uses Docket Alarm's internal VIDA AI to query specific cases. LlamaIndex can call this tool directly to get synthesized legal answers before deciding to pull the full docket text.

Use `list_search_direct_courts` to find out which state courts are supported, then run `search_direct` to pull the records. The resulting documents are then ready for indexing and retrieval.

Your legal queries and court records are processed in memory through Vinkius's isolated runtime. No docket data or search parameters are cached on public servers, keeping your firm's research confidential.

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