How to Use the AdaptiveWork (Clarizen) MCP in CrewAI

Q: How do I connect AdaptiveWork (Clarizen) to CrewAI?

Pass your Vinkius endpoint URL directly into the mcps array in your Agent definition. For more control, import MCPServerHTTP from crewai.mcp and configure specific transports.

Q: Can CrewAI agents share AdaptiveWork (Clarizen) project data?

Yes. When one agent pulls active task lists using listtasks, that JSON response enters the crew's shared memory. Subsequent agents read that data without needing to make duplicate API calls.

Q: How do I restrict AdaptiveWork (Clarizen) tools to specific CrewAI agents?

Use the toolfilter parameter when setting up your MCP Server connection. This allows you to give read-only tools to a monitor agent while reserving task creation for a manager agent.

Deploy a specialized crew of autonomous agents to monitor and manage your AdaptiveWork portfolios using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdaptiveWork (Clarizen) MCP to CrewAI

Create your Vinkius account to connect AdaptiveWork (Clarizen) 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 AdaptiveWork (Clarizen) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Autonomous Project Management Crews

One agent gets confused trying to manage an entire enterprise portfolio. CrewAI lets you split the job up. You assign a Researcher agent to constantly poll `list_projects` and look for stalled initiatives. When the researcher spots a problem, it passes the context to an Analyst agent in shared memory. The Analyst hits `get_project_details` to figure out exactly why metrics are slipping. This MCP Server feeds your entire autonomous team the raw data they need to collaborate.

Delegate Clarizen Task Creation Hierarchically

Top-down execution changes how you handle resource planning. A manager agent reviews the current workload by calling `list_users` to see who has capacity. It then delegates the actual assignment to a subordinate agent. The subordinate takes those instructions and executes `create_task` with the correct parent ID. You do not write any of this routing logic. The framework handles the delegation while the tools handle the actual Clarizen updates.

Isolate Advanced CZQL to Specialist Agents

Writing valid Clarizen Query Language requires specific context that clutters up general-purpose agents. You can use the `tool_filter` feature in `MCPServerHTTP` to expose `run_query` only to a dedicated Database Expert agent. The rest of the crew just asks the expert for custom data retrieval. The expert writes the CZQL syntax, grabs the precise portfolio metrics, and drops the results back into the crew's shared memory.

Setup guide

Set up AdaptiveWork (Clarizen) 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 AdaptiveWork (Clarizen) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent AdaptiveWork (Clarizen) 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="AdaptiveWork (Clarizen) Analyst",
        goal="Access and analyze AdaptiveWork (Clarizen) data via MCP.",
        backstory="Expert analyst with direct AdaptiveWork (Clarizen) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent AdaptiveWork (Clarizen) 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 AdaptiveWork. 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 AdaptiveWork (Clarizen) 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 AdaptiveWork (Clarizen) MCP in CrewAI

Pass your Vinkius endpoint URL directly into the `mcps` array in your Agent definition. For more control, import `MCPServerHTTP` from `crewai.mcp` and configure specific transports.

Yes. When one agent pulls active task lists using `list_tasks`, that JSON response enters the crew's shared memory. Subsequent agents read that data without needing to make duplicate API calls.

Use the `tool_filter` parameter when setting up your MCP Server connection. This allows you to give read-only tools to a monitor agent while reserving task creation for a manager agent.

Hierarchical execution shines here. A planner agent can evaluate user capacity, then direct worker agents to spin up granular tasks across multiple project containers simultaneously.

Only your authenticated endpoints. Vinkius wraps every request in a hardened V8 isolate that processes your user lists and custom query results ephemerally. The execution space vanishes the moment the data transfers to your local crew.

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