How to Use the Docket Alarm MCP in Pydantic AI

Q: How do I register the Docket Alarm MCP Server with Pydantic AI?

You use the MCPToolset class pointing to your Vinkius HTTP endpoint and pass it to your agent's toolsets parameter. This exposes all thirteen legal research MCP tools to your model with automatic runtime schema validation.

Q: Does the Docket Alarm integration support direct state court searches in Pydantic AI?

Yes, you can run searchdirect to query state and agency courts directly. To ensure you provide the correct parameters, have your agent call getsearchdirectargs first to fetch the required search schema for that specific court.

Q: How do I run natural language queries against court records safely?

Use smartsearch to convert plain English descriptions into complex, structured search queries. This tool handles the syntax generation, minimizing search errors and ensuring your agent finds the exact filings you need.

Build type-safe legal agents with Pydantic AI that validate every Docket Alarm search and docket update at runtime.

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 Pydantic AI

Create your Vinkius account to connect Docket Alarm to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Court Searches via Pydantic AI

The `search` tool queries the database of over 732 million legal records and returns structured search results. By running this through this MCP Server, your agent validates the schema of every returned case match before passing it to your LLM. This prevents silent failures caused by unexpected API payload changes. When targeting federal records, use `search_pacer` to run direct queries against PACER databases. The tool returns detailed case listings that your agent can parse with strict type safety. This guarantees that docket numbers, party names, and filing dates map perfectly to your internal Python data models.

Monitor Active Dockets with Type Validation

The `track_case` tool registers active court cases for automatic tracking so your agent gets notified of new filings. Because Pydantic AI enforces strict schemas, any incoming alert data is validated against your models before hitting your database. This keeps your litigation tracking pipeline clean and free of corrupt records. To inspect the current state of any tracked case, use `get_docket` to retrieve the full, live docket sheet. This MCP tool ensures your attorneys are working with real-time data when drafting motions or preparing for trial. You can disable caching to pull the absolute latest filings directly from the court clerk.

Extract Structured Insights from Complaints

The `get_complaint_summary` tool parses raw legal complaints and extracts structured summaries of the allegations. Your agent can demand specific output fields, like plaintiff demands or key factual claims, and validate them at runtime. This turns unstructured legal prose into reliable, typed data for your downstream workflows. You can combine this with `extract_judgment` to pull clean outcomes and damages from final court orders. The tool isolates the exact ruling, preventing the model from hallucinating numbers or misinterpreting the judge's decision. This gives you a bulletproof pipeline for tracking litigation success rates.

Setup guide

Set up Docket Alarm MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "docket-alarm-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Docket Alarm tools.",
)

result = await agent.run("List recent Docket Alarm transactions")
print(result.output)

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 Pydantic AI

You use the `MCPToolset` class pointing to your Vinkius HTTP endpoint and pass it to your agent's `toolsets` parameter. This exposes all thirteen legal research MCP tools to your model with automatic runtime schema validation.

Yes, you can run `search_direct` to query state and agency courts directly. To ensure you provide the correct parameters, have your agent call `get_search_direct_args` first to fetch the required search schema for that specific court.

Your Pydantic AI agent will fail loudly with a validation error rather than silently passing corrupt data to your model. This ensures your litigation pipeline only processes clean, correctly formatted docket records.

Use `smart_search` to convert plain English descriptions into complex, structured search queries. This tool handles the syntax generation, minimizing search errors and ensuring your agent finds the exact filings you need.

All interactions with court records, search queries, and PACER credentials run inside isolated V8 sandboxes using this MCP Server. No search terms or fetched legal documents are stored on disk or used for training models. Your firm's active litigation investigations remain strictly 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