How to Use the Clio MCP in AutoGen

Q: Does AutoGen need a special adapter for these Clio tools?

Yes, you'll need the autogen-extmcp package. It includes the mcpservertools function which fetches the tools from your Vinkius endpoint and makes them available to your AssistantAgent. The adapter handles all the schema conversions for you.

Let your AutoGen agents debate and manage your legal practice. Build multi-agent systems that collaborate on tasks in Clio.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clio MCP to AutoGen

Create your Vinkius account to connect Clio 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 Clio with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Delegate Case Intake to a Team

Set up a conversation between a "Client Intake Agent" and a "Case Analyst Agent." The intake agent talks to the user and calls `create_contact`. It then passes the new contact ID to the analyst agent in the chat. The analyst takes over, using `create_matter` to open the case and `create_task` to assign initial to-dos. This isn't a rigid script; it's a collaborative workflow where agents delegate work to each other.

Run a Compliance Review with Agents

Imagine a "Billing Agent" that uses `list_activities` to review all new time entries. It can flag any entry that seems vague or incomplete. A "Supervising Attorney Agent" then joins the conversation to review the flagged items. The supervisor agent can approve the time or use `create_note` on the matter to ask the original attorney for more detail. This consensus-driven approach helps your team catch errors through automated, internal debate.

Your Clio Tools for AutoGen Conversations

This MCP Server gives your team of agents a shared toolbox with 23 Clio functions. You can create specialized agents: one that's an expert at finding information with `search_contacts` and `search_matters`, and another that's responsible for execution with `create_task` and `create_note`. They work together by discussing the problem, sharing data they've found, and deciding as a group on the best course of action. It's a powerful way to model how a real legal team collaborates.

Setup guide

Set up Clio 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 Clio 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="Clio_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

AutoGen agents decide through conversation. Based on the user's prompt and the ongoing discussion, the LLM determines which agent should act next and which of its available Clio tools is the right one for the job. It's a more dynamic process than a simple if/then script.

Absolutely. This is a perfect use case for AutoGen. You can assign the `list_` and `search_` tools to the paralegal agent for research, and the `create_` tools to the attorney agent for taking action. They can then collaborate in a chat to manage a Clio matter.

The server provides a wide range of specific, single-purpose tools. This granularity is ideal for AutoGen, as you can assign different sets of tools to different agents, creating specialists that can then debate and collaborate to solve a larger problem.

Yes, you'll need the `autogen-ext[mcp]` package. It includes the `mcp_server_tools` function which fetches the tools from your Vinkius endpoint and makes them available to your AssistantAgent. The adapter handles all the schema conversions for you.

Vinkius handles authentication for every tool call to the Clio MCP server. Your agents access data like financial records from `get_bill` or time entries from `list_activities` through a secure proxy. The tools run in sandboxed, single-use environments, ensuring your firm's data isn't exposed.

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