How to Use the DISCO MCP in AutoGen

Q: How do AutoGen agents collaborate when searching DISCO files?

One agent uses searchmatterdocuments to gather raw search results, while another agent analyzes those files using getdocumentmetadata. They debate the relevance of the findings in a group chat before presenting the final list.

Q: How does AutoGen handle tool execution errors from DISCO?

When a tool like getmatterdetails fails or returns an error, the executing agent communicates the failure to the group. The coordinator agent can then decide to retry the call or adjust the search parameters.

Q: How do I register DISCO tools with my AutoGen assistant?

Use the mcpservertools adapter to load tools from your Vinkius HTTP server endpoint. Pass the resulting tool list directly to your AssistantAgent constructor to give them access to listlegalmatters.

Q: What security measures protect my DISCO user lists and document metadata?

All operations, including calls to listauthorizedusers and getdocumentmetadata, run inside an isolated, zero-trust V8 sandbox. Your sensitive user directories and litigation metadata are never cached, stored, or exposed to external networks.

AutoGen agents debate and coordinate to manage DISCO legal matters, audit access, and track document ingestion.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DISCO MCP to AutoGen

Create your Vinkius account to connect DISCO 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 DISCO with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent reviews using the DISCO MCP Server

AutoGen lets you deploy specialized agents that work together on legal operations. A litigation support agent can call `list_recently_ingested_documents` to find new files, while a separate compliance agent reviews the output to flag potential issues. The agents debate whether the correct tags are applied by checking `list_document_tags` using our MCP client and only proceed to update the case file once they reach a consensus.

Audit user access through multi-agent consensus

Security audits shouldn't be left to a single prompt. In AutoGen, a security agent can pull the active user list using `list_matter_access_users` and challenge a project manager agent on why certain external users have access to a matter. The agents cross-reference the output of `list_authorized_users` with the details from `get_matter_details`. They negotiate and flag discrepancies, ensuring your litigation data remains locked down.

Automated document validation pipelines

Set up an AutoGen group chat where agents handle document ingestion quality control. One agent runs `search_matter_documents` to find files missing metadata, and another agent analyzes the output of `get_document_metadata` to find structural anomalies. If the metadata agent finds a corrupt file, it notifies the ingestion agent to flag it. This automated teamwork ensures that your document database is clean and ready for legal review without manual checking.

Setup guide

Set up DISCO 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 DISCO 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="DISCO_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

One agent uses `search_matter_documents` to gather raw search results, while another agent analyzes those files using `get_document_metadata`. They debate the relevance of the findings in a group chat before presenting the final list.

Yes, you can set up a compliance agent that regularly calls `list_matter_access_users` and compares it to a master list. The agent debates access rights with a manager agent to flag unauthorized external users.

When a tool like `get_matter_details` fails or returns an error, the executing agent communicates the failure to the group. The coordinator agent can then decide to retry the call or adjust the search parameters.

Use the mcp_server_tools adapter to load tools from your Vinkius HTTP server endpoint. Pass the resulting tool list directly to your AssistantAgent constructor to give them access to `list_legal_matters`.

All operations, including calls to `list_authorized_users` and `get_document_metadata`, run inside an isolated, zero-trust V8 sandbox. Your sensitive user directories and litigation metadata are never cached, stored, or exposed to external networks.

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