How to Use the Docket Alarm MCP in Vercel AI SDK

Q: How do I handle PACER fees when using Docket Alarm with Vercel AI SDK?

You control fees by configuring the searchpacer and getdocket tools to use cached results by default. Set test=true during development in your Next.js API routes to run queries without incurring the standard $0.10 per-page PACER fee.

Q: Can I stream live case tracking alerts using Vercel AI SDK and Docket Alarm?

Yes, you can initiate real-time tracking by invoking trackcase inside your server actions. The Vercel AI SDK streams the confirmation payload back to your React frontend, verifying that the new docket activity alerts are active.

Q: What is the fastest way to set up the Docket Alarm MCP Server using Vercel AI SDK?

Run npm install ai @ai-sdk/mcp and instantiate the client with createMCPClient. You then import the tools into your route handler, feed them to streamText, and call mcpClient.close() when the stream finishes.

Q: How does smartsearch handle natural language legal queries?

The smartsearch tool translates conversational legal questions into structured boolean queries. It analyzes the user's raw input and outputs formatted search syntax that matches the Docket Alarm database schema.

Q: How does the Vercel AI SDK integration protect sensitive court records and search histories?

All requests to getdocket and extractjudgment run inside a zero-trust, ephemeral V8 isolate. Your PACER credentials and legal search histories are never stored on Vinkius, ensuring your firm's work product remains confidential.

Feed live court dockets and PACER data directly into your React frontends with Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Docket Alarm to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Docket Streaming with Vercel AI SDK

The `get_docket` tool pulls real-time court records directly into your Next.js application—without making users wait for a full page reload. By passing this tool to `streamText`, the docket sheet renders row-by-row as the data arrives from the court. This stops the typical loading spinner fatigue that plagues legal tech. Users see active PACER updates immediately, while Edge Functions keep your MCP connection tokens completely hidden from the client browser.

Extract Case Insights Directly to UI

The `get_complaint_summary` tool uses legal-specific language models to parse long, dense complaints into readable summaries—letting attorneys scan causes of action instantly. Your frontend can render these summaries live as they generate, letting users scan key allegations without opening massive PDFs. You register the tool via `createMCPClient` and pass it to your text generation functions. The Vercel AI SDK handles the underlying JSON streaming, so your interface updates dynamically without blocking the main execution thread.

Dynamic State and Agency Searches

The `list_search_direct_courts` tool exposes the exact state and agency tribunals supported for direct, non-PACER searches. Your React components can query this list to build dynamic dropdowns that guide users to the right jurisdiction. Once the user selects a court, `get_search_direct_args` fetches the specific parameters required for that venue. The entire interaction runs through the Vercel AI SDK interface, ensuring users only input valid search terms before hitting state databases.

Setup guide

Set up Docket Alarm MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Docket Alarm tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Docket Alarm transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You control fees by configuring the `search_pacer` and `get_docket` tools to use cached results by default. Set `test=true` during development in your Next.js API routes to run queries without incurring the standard $0.10 per-page PACER fee.

Yes, you can initiate real-time tracking by invoking `track_case` inside your server actions. The Vercel AI SDK streams the confirmation payload back to your React frontend, verifying that the new docket activity alerts are active.

Run `npm install ai @ai-sdk/mcp` and instantiate the client with `createMCPClient`. You then import the tools into your route handler, feed them to `streamText`, and call `mcpClient.close()` when the stream finishes.

The `smart_search` tool translates conversational legal questions into structured boolean queries. It analyzes the user's raw input and outputs formatted search syntax that matches the Docket Alarm database schema.

All requests to `get_docket` and `extract_judgment` run inside a zero-trust, ephemeral V8 isolate. Your PACER credentials and legal search histories are never stored on Vinkius, ensuring your firm's work product remains 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