How to Use the CourtListener MCP in AutoGen

Q: How do I give AutoGen access to CourtListener?

Install autogen-extmcp. Initialize mcpservertools with a StreamableHttpServerParams pointing to your Vinkius URL.

Q: Can multiple AutoGen agents share the CourtListener tools?

Pass the generated tool list to the constructor of any AssistantAgent that needs to pull case law. They can all call the endpoints independently.

Deploy debating AutoGen agents that argue case strategy using live CourtListener dockets and citations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CourtListener MCP to AutoGen

Create your Vinkius account to connect CourtListener 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 CourtListener with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Debate on Precedent

Assign one agent to find supporting cases with `search_opinions`. Task a second agent to play devil's advocate by running `list_citations` to find where those cases were overturned. They argue the merits back and forth in your terminal. You get a synthesized legal strategy that survived aggressive internal scrutiny.

AutoGen MCP Server for Conflict Checks

Set up a dedicated compliance agent armed with `get_judge` and `list_financial_disclosures`. While your research agent builds the case, the compliance agent scans the bench for stock ownership conflicts. If the compliance bot finds a red flag, it interrupts the conversation. The agents negotiate whether to request a recusal or proceed with the current strategy.

Autonomous Docket Monitoring

Give a background agent access to `search_dockets`. It polls the database for updates on specific filings while your primary agents discuss the broader legal theory. The `McpToolAdapter` handles all the schema conversions behind the scenes. Your agents just read the JSON output and adjust their arguments based on the latest court filings.

Setup guide

Set up CourtListener 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 CourtListener 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="CourtListener_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent CourtListener 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="CourtListener_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent CourtListener 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 CourtListener. 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 CourtListener 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 CourtListener MCP in AutoGen

Install `autogen-ext[mcp]`. Initialize `mcp_server_tools` with a `StreamableHttpServerParams` pointing to your Vinkius URL.

Pass the generated tool list to the constructor of any `AssistantAgent` that needs to pull case law. They can all call the endpoints independently.

One agent executes a search. The other agents read the results in the shared chat history and debate what the findings mean for your case.

No. The MCP framework automatically translates the server definitions into native tool calling formats. Your agents understand the parameters out of the box.

Vinkius operates a strict zero-trust sandbox. The specific dockets, financial disclosures, and citation lists your agents debate vanish the moment the ephemeral session ends. We do not inspect your legal queries.

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