How to Use the DeskTime MCP in CrewAI

Q: How do I give a CrewAI agent access to DeskTime tools?

The easiest way is to pip install crewaitools and then pass your Vinkius MCP URL into the mcps list when you define an agent. CrewAI handles the connection and tool discovery for you.

Q: How can I stop some CrewAI agents from deleting DeskTime projects?

Use the toolfilter option when you set up the MCPServerHTTP connection. This lets you create different connection objects for different agents, exposing only the tools they're allowed to use. You'd simply omit removeproject for most agents.

Deploy autonomous agent crews to manage your DeskTime account. Let a CrewAI team handle project oversight, productivity monitoring, and reporting.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeskTime MCP to CrewAI

Create your Vinkius account to connect DeskTime 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 DeskTime with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy an Autonomous Project Admin Crew

Assemble a team of agents to manage your projects. One agent, the 'Analyst', can use `list_projects` and `get_project_details` to monitor progress. It can then pass tasks to a 'Coordinator' agent, which uses `create_new_task` to assign work. This shows the power of CrewAI's collaborative model. You can even add an 'Archivist' agent to the crew. Its only job is to use the `remove_project` tool to clean up old, completed projects that the Analyst flags for deletion.

Run a Workforce Productivity Monitoring Team

A CrewAI team is perfect for continuous monitoring. Set up a 'Scout' agent to run `list_online_staff` periodically. If it notices something unusual, it delegates to a 'Performance' agent that uses `get_employee_performance` to dig deeper. A 'Reporter' agent can then take the findings from the other two, pull a high-level summary with `get_productivity_reports`, and compile a daily brief. The entire process runs autonomously.

Specialize Agent Roles with This MCP Server

You don't have to give every agent the keys to the kingdom. With CrewAI, you can assign specific tools from this MCP server to specific agents, enforcing a separation of duties. For example, your monitoring agents might only get read-access tools like `list_employees`. Meanwhile, only a trusted 'Manager' agent would get access to write-access tools like `create_project` or the highly-sensitive `remove_project`. This lets you build safer, more predictable autonomous systems.

Setup guide

Set up DeskTime 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 DeskTime tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The easiest way is to `pip install crewai[tools]` and then pass your Vinkius MCP URL into the `mcps` list when you define an agent. CrewAI handles the connection and tool discovery for you.

Yes, that's a perfect use for a sequential crew. The first agent can use `get_employee_performance`, analyze the output, and then pass its findings and instructions to a second agent that uses `create_new_task` to act on them.

Use the `tool_filter` option when you set up the `MCPServerHTTP` connection. This lets you create different connection objects for different agents, exposing only the tools they're allowed to use. You'd simply omit `remove_project` for most agents.

A hierarchical crew would work well for project management. You could have a 'Project Manager' agent that oversees multiple 'Worker' agents. The manager could use `get_project_details` to assess status and then delegate `create_new_task` calls to the workers.

It only accesses your DeskTime account's project, task, and employee productivity data. Each tool call from your agent runs in a zero-trust, ephemeral sandbox on Vinkius, which is immediately destroyed after the call completes. Nothing is logged or retained.

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