How to Use the Actionstep MCP in LangChain

Connect your law practice data to LangChain agents for custom reasoning pipelines.

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 LangChain

Create your Vinkius account to connect Actionstep to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build LangChain legal workflows

The Actionstep MCP Server lets your ReAct agents pull case data through `get_matter_details` and `list_action_types`. You define the chain, and the agent decides when to fetch specific matter information based on user prompts. Output from those queries feeds directly into the next step of your pipeline. LangSmith handles the tracing, so you see exactly how many tokens your agent burned while reading through `list_matter_notes`.

Automate billable time tracking

Your agent pulls current hours using `list_time_entries` to calculate client balances. This keeps your billing data in sync across whatever custom dashboards you build. You skip the manual export process entirely. The framework routes the raw time logs into your downstream processing chains without human intervention.

Manage legal contacts dynamically

Feeding client lists into your application happens through `list_contacts`. If an agent detects a missing party during a document review, it fires off `create_contact` to add them instantly. That immediate write capability turns a static RAG setup into an active participant. Your code handles the logic while the Vinkius MCP endpoint manages the actual API transaction securely.

Setup guide

Set up Actionstep MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Actionstep tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "actionstep-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Actionstep transactions"
    })
    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 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 LangChain

Install the langchain-mcp-adapters package first. Then pass your Vinkius endpoint URL to the MultiServerMCPClient constructor.

Yes, LangSmith captures every request. You see the exact inputs and outputs for operations like fetching matter notes.

It stays stateless by default. Call client.session() if you need your agent to remember previous case details across multiple turns.

The server returns raw JSON arrays for lists and nested objects for specific records. Your code parses these directly into intermediate chain steps.

Vinkius runs your connection inside an ephemeral V8 Isolate Sandbox. Your billable time entries, client contacts, and matter notes never touch disk, and the zero-trust architecture destroys the instance immediately after the chain finishes executing.

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