How to Use the Actionstep MCP in OpenAI Agents SDK

Q: How do I connect Actionstep to the OpenAI Agents SDK?

Install the openai-agents package via pip. Create an MCPServerStreamableHttp instance with your Vinkius URL and pass it to the mcpservers array in your Agent constructor. Set cacheToolsList=True to speed up initialization.

Q: Can my OpenAI Agents SDK system read specific case notes in Actionstep?

Yes. The agent calls listmatternotes to pull file notes for a given matter ID. It reads the raw text, letting your model summarize long case histories or find specific details.

Q: Does this MCP server support agent handoffs in the OpenAI Agents SDK?

Yes, it does. You build a routing agent that checks listactiontypes, then hands off the request to a specialized agent equipped with getmatterdetails to handle the specific case type.

Connect your law practice to the OpenAI Agents SDK via this MCP Server. Read matters and manage contacts directly from production Python.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Actionstep MCP to OpenAI Agents SDK

Create your Vinkius account to connect Actionstep to OpenAI Agents SDK 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 Actionstep with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Actionstep MCP Server for legal tasks

The `list_legal_tasks` tool pulls your active workflow items straight into your Python agent. Your code sees exactly what needs attention across your firm without scraping a web interface. You drop this directly into your OpenAI agent setup using `MCPServerStreamableHttp`. The built-in guardrails validate the task data before execution, keeping hallucinated deadlines out of your production system.

Track billable hours automatically

Agents use `list_time_entries` to pull historical billing records for specific matters. This feeds raw financial data into your specialized billing agent for auditing or invoice generation. Handoffs make this setup powerful. One agent uses `get_matter_details` to read the case context, then passes control to a billing specialist agent that checks the time entries against firm guidelines.

Manage clients and case files

The `create_contact` and `list_contacts` tools give your AI client read-write access to your firm's address book. You build workflows that automatically register new leads from intake forms. Pair this with `list_matters` and `list_matter_notes` to give your agent full context on a client's history. The OpenAI dashboard traces every API call, so you always know exactly when your agent touched a sensitive case file.

Setup guide

Set up Actionstep MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Actionstep tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Actionstep tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Actionstep tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Actionstep Agent",
            instructions="You have access to Actionstep tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Actionstep. 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 Actionstep 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 Actionstep MCP in OpenAI Agents SDK

Install the `openai-agents` package via pip. Create an `MCPServerStreamableHttp` instance with your Vinkius URL and pass it to the `mcp_servers` array in your Agent constructor. Set `cacheToolsList=True` to speed up initialization.

Yes. The agent calls `list_matter_notes` to pull file notes for a given matter ID. It reads the raw text, letting your model summarize long case histories or find specific details.

OpenAI's built-in guardrails catch the error. Before the agent executes `create_contact`, the SDK validates the parameters against the tool's schema. Invalid requests fail before hitting the API.

Yes, it does. You build a routing agent that checks `list_action_types`, then hands off the request to a specialized agent equipped with `get_matter_details` to handle the specific case type.

Vinkius runs the server in an ephemeral V8 Isolate Sandbox. When your agent accesses billable time entries, matter notes, or client contacts, the connection is zero-trust. Data passes through a single endpoint token and vanishes from memory the moment the request completes.

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