How to Use the UniCourt MCP in AutoGen

Q: How does UniCourt aid case searches in AutoGen?

Agents use the searchcases tool to pull initial data. If one agent finds a promising record, it passes that specific case ID to another agent for deeper analysis using getcase, forcing deliberation.

Q: How does UniCourt help with data export requests in AutoGen?

An agent can initiate an export using requestcaseexport. Another agent monitors this process by checking the status via getcaseupdatestatus, ensuring no manual follow-up is needed.

Q: What data privacy features exist with UniCourt and AutoGen?

The server touches case records, specifically party names (searchnormparty) and court documents. The multi-agent system allows you to build checks into the process that flag potential sensitive data points before they are acted upon.

Drive consensus on UniCourt legal research using AutoGen's multi-agent framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect UniCourt MCP to AutoGen

Create your Vinkius account to connect UniCourt to AutoGen 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 UniCourt with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-perspective case analysis with the MCP Server.

You can set up a debate where one agent uses `get_case` to pull raw record data, while another agent uses `search_cases` for broader context. The agents then challenge each other's conclusions based on conflicting inputs.

Systematically analyze normalized legal entities with UniCourt and AutoGen.

Multiple autonomous agents can collaborate to vet entity information. One agent might use `get_norm_attorney` for details, while a second checks the firm association using `get_norm_law_firm`. They debate which combination of data points is most accurate.

Automate credential management and tracking with UniCourt/AutoGen.

Agents can handle maintenance tasks. A 'security' agent might run `get_pacer_credential` to check access, while a 'tracking' agent uses `track_case`. They negotiate the best time and method for updating credentials.

Setup guide

Set up UniCourt MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes UniCourt tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="UniCourt_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent UniCourt data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="UniCourt_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent UniCourt data")
    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 UniCourt. 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 UniCourt 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 UniCourt MCP in AutoGen

Agents use the `search_cases` tool to pull initial data. If one agent finds a promising record, it passes that specific case ID to another agent for deeper analysis using `get_case`, forcing deliberation.

Yes. You can assign an agent the task of scheduling updates via `track_case`. This repeatable process ensures that multiple agents are constantly challenging and validating the freshness of your data.

AutoGen can compare records for attorneys, judges, firms, and parties. By calling tools like `get_norm_judge` or `get_norm_law_firm`, the agents debate which specific metrics are most relevant for a given legal query.

An agent can initiate an export using `request_case_export`. Another agent monitors this process by checking the status via `get_case_update_status`, ensuring no manual follow-up is needed.

The server touches case records, specifically party names (`search_norm_party`) and court documents. The multi-agent system allows you to build checks into the process that flag potential sensitive data points before they are acted upon.

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