How to Use the Lunatask MCP in CrewAI

Q: Can a CrewAI agent read the text of my Lunatask notes?

No. The listnotesmetadata tool only returns structural metadata, not the actual text content of your notes. Your private thoughts and documentation remain encrypted and completely inaccessible to the agents.

Run autonomous multi-agent teams to manage your Lunatask workspace securely using CrewAI and a secure MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lunatask MCP to CrewAI

Create your Vinkius account to connect Lunatask 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 Lunatask with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate productivity crews with CrewAI

Coordinate productivity crews with CrewAI to analyze your daily schedule. Set up a crew where one specialized agent analyzes your productivity patterns while another updates your schedule. By using the `list_tasks_metadata` and `get_task_metadata` tools, your analyst agent can review your workload patterns without ever seeing the raw text of your tasks. Once the analysis is complete, a coordinator agent can use `update_existing_task` or `create_new_task` to adjust your schedule. The agents collaborate using shared memory, ensuring that task updates are consistent across your entire workspace.

Automated habit and routine maintenance

Let your agents keep your habits on track without constant manual check-ins. Your crew can monitor external triggers and call `track_habit_completion` whenever you finish a scheduled milestone. This keeps your momentum going without requiring you to open the app. You can also have an agent inspect your habits and write summaries using `create_journal_entry`. A continuous feedback loop is created where your achievements are documented and saved securely in your private journal.

Secure workspace cleanup operations

Run regular maintenance crews to prune your task list and archive old items. An agent can use `list_tasks_metadata` to find tasks that haven't been updated in weeks, then systematically clean them up using `delete_task`. This cleanup process runs autonomously in the background, keeping your workspace fast and responsive. Because the crew only interacts with metadata, your private task details remain completely hidden from the underlying models.

Setup guide

Set up Lunatask 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 Lunatask tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Lunatask 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 Lunatask. 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 Lunatask 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 Lunatask MCP in CrewAI

You can pass the HTTP endpoint URL directly into the agent's `mcps` configuration list during initialization. For more advanced setups, use the `MCPServerHTTP` class from `crewai.mcp` to filter which tools are exposed to specific agents.

No. The `list_notes_metadata` tool only returns structural metadata, not the actual text content of your notes. Your private thoughts and documentation remain encrypted and completely inaccessible to the agents.

Yes, you can define sequential processes where Agent A lists tasks using `list_tasks_metadata` and Agent B updates them using `update_existing_task`. This ensures your workspace is modified in a predictable, step-by-step manner.

You can use CrewAI's tool filtering options to expose only the `create_new_task` tool to that specific agent. This prevents the agent from accessing destructive tools like `delete_task` or reading metadata.

Your data remains stored securely in Lunatask's encrypted database. The MCP server only acts as a secure, ephemeral bridge that handles metadata and IDs, ensuring no plaintext task descriptions or journal contents are cached or logged.

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