How to Use the timeghost MCP in CrewAI

Q: How do I limit tool access for specific agents in CrewAI?

Use the toolfilter option in your MCP configuration to restrict access. This ensures only your designated 'Admin' agent can call tools like listtimeghostworkspaces.

Coordinate specialized agents in CrewAI to manage your team's time tracking operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect timeghost MCP to CrewAI

Create your Vinkius account to connect timeghost to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup timeghost with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Collaborative tracking with CrewAI agents

Assign a researcher agent to fetch project details using `get_timeghost_project` while a moderator agent verifies the entries. This allows your crew to handle complex tracking tasks without human oversight. By leveraging shared memory, your agents can hand off data from `list_timeghost_projects` to the next agent in the sequence. Each agent only sees what it needs to complete its specific part of the operation.

Hierarchical management of time logs

Set up a lead agent that manages the entire workspace using `list_timeghost_workspaces`. It can delegate specific entry tasks to sub-agents, ensuring a clean division of labor. This structure is perfect for auditing. The lead agent uses `list_timeghost_entries` to gather the week's logs, then passes them to an analyst agent for validation.

Automated reporting through specialized roles

Create a report-generator agent that pulls lists of clients via `list_timeghost_clients`. It can compile this data into a summary for your management team, saving hours of manual admin work. Your agents can also use `list_timeghost_members` to track individual performance against set goals. This gives you a clear picture of team velocity without manual reporting.

Setup guide

Set up timeghost 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 timeghost tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the tool list directly into the agent definition in your CrewAI setup. This limits which agents can access specific functions like `get_timeghost_task`.

Yes, CrewAI agents share memory by default. Once an agent fetches data with `list_timeghost_entries`, the rest of the crew can access that information to inform their next actions.

Use the tool_filter option in your MCP configuration to restrict access. This ensures only your designated 'Admin' agent can call tools like `list_timeghost_workspaces`.

It does. You can define a process where one agent fetches tasks via `list_timeghost_tasks` and then passes them to a second agent to check their status.

The MCP Server maintains a strict sandbox for your credentials. Your time logs and project names never leave your local environment, ensuring that only your authorized crew can access them.

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