How to Use the Toggl Plan MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle complex updates for Toggl Plan?

The agent uses the updatetimelinetask tool. You pass a JSON object containing the changes you want to make. Because this runs in a production context, your AI client ensures the payload is structured correctly before sending it.

Q: What data types can I retrieve about my Toggl Plan workspace using OpenAI Agents SDK?

You can pull user lists with listworkspaceusers, see all available tags via listworkspacetags, and get a comprehensive list of projects by calling listworkspaceprojects.

Q: Can the OpenAI Agents SDK delete tasks from Toggl Plan?

Yes, the agent has access to deletetimelinetask. Just remember that this action is permanent and cannot be undone, so you'll want to use it carefully.

Q: Is the OpenAI Agents SDK suitable for reading task details from Toggl Plan?

Absolutely. You can retrieve specific timeline tasks using gettaskdetails, or list every single task in a workspace with listtimelinetasks.

Build production agents for managing project timelines with OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Toggl Plan MCP to OpenAI Agents SDK

Create your Vinkius account to connect Toggl Plan to OpenAI Agents SDK 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 Toggl Plan with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Project Timelines

Your agent uses `list_timeline_tasks` to pull a full list of tasks from the workspace. This gives your system an immediate overview of what's happening across all projects, letting you check dependencies and current phases. You can then write or change details using `create_timeline_task` or `update_timeline_task`. This means the agent doesn't just read data; it actively manages the project schedule when needed.

Understand Project Structure

Need to know what projects exist? The tool `list_workspace_projects` fetches all active projects in a given workspace. It also lets your agent look up specific details using `get_project_details`, which is useful for building complex, multi-step workflows. If you need context on the teams involved or what data needs tracking, use `list_workspace_users` and `list_workspace_tags`. These calls give your AI client the full picture of who owns the work.

Maintain Data Integrity

The agent handles task modifications with `delete_timeline_task`, permanently removing items from the timeline. Since this action is irreversible, using it within a guardrail system is critical for safety. For read operations, you can get specific details on single tasks via `get_task_details` or see all key project milestones by calling `list_milestones`. This level of granularity ensures your agent only acts with verified data.

Setup guide

Set up Toggl Plan MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Toggl Plan tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Toggl Plan tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Toggl Plan tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Toggl Plan Agent",
            instructions="You have access to Toggl Plan tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Toggl Plan. 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 Toggl Plan 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 Toggl Plan MCP in OpenAI Agents SDK

The agent uses the `update_timeline_task` tool. You pass a JSON object containing the changes you want to make. Because this runs in a production context, your AI client ensures the payload is structured correctly before sending it.

You can pull user lists with `list_workspace_users`, see all available tags via `list_workspace_tags`, and get a comprehensive list of projects by calling `list_workspace_projects`.

Yes, the agent has access to `delete_timeline_task`. Just remember that this action is permanent and cannot be undone, so you'll want to use it carefully.

Absolutely. You can retrieve specific timeline tasks using `get_task_details`, or list every single task in a workspace with `list_timeline_tasks`.

This MCP Server handles project metadata, user credentials, task names, and associated IDs (workspace ID, project ID). It's all about structured productivity data.

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