How to Use the Actionstep MCP in CrewAI

Q: Is it possible to filter Actionstep tools in CrewAI?

Yes, use the toolfilter option to limit which agents see which tools. You might give your research agent list-only access while keeping creation tools for your moderator agent.

Deploy a crew of specialized agents to manage your Actionstep legal practice autonomously.

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 CrewAI

Create your Vinkius account to connect Actionstep to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

CrewAI agents managing Actionstep matter files

Assign a research agent to call `list_matters` and a moderator agent to review the output. They share context to ensure no file goes unreviewed. This setup automates the drudgery of legal administration. The crew works through your caseload while you focus on high-level decisions.

Autonomous legal operations with Actionstep and CrewAI

Set up a crew that monitors `list_legal_tasks` and escalates pending items to the right staff. The agents operate in a sequence you define. They don't stop for coffee. They check the tasks, update the status, and move to the next item in the queue.

Shared memory between CrewAI agents for Actionstep

Agents use shared memory to track `list_time_entries` across multiple sessions. If one agent finds a discrepancy, the next agent picks it up for investigation. Collaboration happens at machine speed. You get a cohesive team of agents that understand the state of your practice at all times.

Setup guide

Set up Actionstep MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Actionstep tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Actionstep Analyst",
    goal="Access and analyze Actionstep data via MCP.",
    backstory="Expert analyst with direct Actionstep access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Actionstep transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Actionstep Analyst",
        goal="Access and analyze Actionstep data via MCP.",
        backstory="Expert analyst with direct Actionstep access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Actionstep transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the server URL to your agent definition in the mcps list. The agents then gain the ability to list matters, notes, and contacts based on your instructions.

They can. By using shared memory, one agent can list the tasks and another can process them, creating a pipeline that handles your entire legal workflow.

Yes, use the tool_filter option to limit which agents see which tools. You might give your research agent list-only access while keeping creation tools for your moderator agent.

You can connect using stdio, SSE, or Streamable HTTP. Choose the transport that fits your environment, and the agents will handle the rest.

We enforce strict ephemeral boundaries for every agent session. Your Actionstep matter notes are processed in a zero-trust sandbox that wipes all record of the data the moment the task finishes.

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