Where do I obtain my Toggl Plan Access Token?

Navigate to the Toggl Plan web panel, head over to your **Profile settings**, and locate the Developer/API Integrations segment. You will need a valid Access Token (often labeled API or OAuth Bearer token in your administrative view). Create it permanently and keep the exposed hash secure.

Does the system support permanent deletion of elements?

Yes. This connector features a `delete_timeline_task` handler. If specifically instructed by you, the AI agent is capable of making a permanent removal request which cannot be un-done. You should instruct the AI cautiously when using mutations.

Are there any data sync delays when updating timelines with the agent?

No. Toggl Plan's API ensures immediate reflection of all timeline and milestone changes. When the agent updates a task or resource allocation, it instantly appears in the web interface for all workspace users without any caching delays.

Toggl Plan MCP Server for LlamaIndex 10 tools — connect in under 2 minutes

Name: Toggl Plan
Availability: InStock
Author: Vinkius

docs.llamaindex.ai/en/stable/module_guides/tools/mcp

Built by Vinkius GDPR 10 Tools Framework

LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Toggl Plan as an MCP tool provider through the Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    agent = FunctionAgent(
        tools=tools,
        llm=OpenAI(model="gpt-4o"),
        system_prompt=(
            "You are an assistant with access to Toggl Plan. "
            "You have 10 tools available."
        ),
    )

    response = await agent.run(
        "What tools are available in Toggl Plan?"
    )
    print(response)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Toggl Plan MCP Server

Connect your Toggl Plan workspaces to an AI agent entirely bypassing the complex graphical interfaces. Allow your project managers and team leads to directly read, create, and organize workload data, milestones, and daily tasks inside a conversational or command-driven environment.

LlamaIndex agents combine Toggl Plan tool responses with indexed documents for comprehensive, grounded answers. Connect 10 tools through the Vinkius and query live data alongside vector stores and SQL databases in a single turn — ideal for hybrid search, data enrichment, and analytical workflows.

What you can do

Timeline Oversight — Search workspaces to list, read, or inspect the metadata details of specific timeline tasks and milestones
Project Construction — Easily list all the active project segments directly on your terminal to know what your team is facing today
Task Execution — Complete the full cycle of task management: Create new nodes on the timeline, update existing entries, or delete deprecated ones through simple instructions
Fleet Operations — Manage human resources by securely listing all registered workspace users to assign workloads correctly
Taxonomy Organization — Check and retrieve current tagging structures to ensure standardized labels

The Toggl Plan MCP Server exposes 10 tools through the Vinkius. Connect it to LlamaIndex in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Toggl Plan to LlamaIndex via MCP

Follow these steps to integrate the Toggl Plan MCP Server with LlamaIndex.

Install dependencies

Run pip install llama-index-tools-mcp llama-index-llms-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Toggl Plan

Why Use LlamaIndex with the Toggl Plan MCP Server

LlamaIndex provides unique advantages when paired with Toggl Plan through the Model Context Protocol.

Data-first architecture: LlamaIndex agents combine Toggl Plan tool responses with indexed documents for comprehensive, grounded answers

Query pipeline framework lets you chain Toggl Plan tool calls with transformations, filters, and re-rankers in a typed pipeline

Multi-source reasoning: agents can query Toggl Plan, a vector store, and a SQL database in a single turn and synthesize results

Observability integrations show exactly what Toggl Plan tools were called, what data was returned, and how it influenced the final answer

Toggl Plan + LlamaIndex Use Cases

Practical scenarios where LlamaIndex combined with the Toggl Plan MCP Server delivers measurable value.

Hybrid search: combine Toggl Plan real-time data with embedded document indexes for answers that are both current and comprehensive

Data enrichment: query Toggl Plan to augment indexed data with live information before generating user-facing responses

Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying Toggl Plan for fresh data

Analytical workflows: chain Toggl Plan queries with LlamaIndex's data connectors to build multi-source analytical reports

Toggl Plan MCP Tools for LlamaIndex (10)

These 10 tools become available when you connect Toggl Plan to LlamaIndex via MCP:

create_timeline_task

Requires workspace ID, task name, and project ID. Creates a new task on the Toggl Plan timeline

delete_timeline_task

This action is irreversible. Permanently deletes a task from the timeline

get_project_details

Retrieves details for a specific project

get_task_details

Retrieves details for a specific timeline task

list_milestones

Lists all project milestones

list_timeline_tasks

Requires a workspace ID. Lists all tasks on the Toggl Plan timeline for a specific workspace

list_workspace_projects

Lists all projects in a specific Toggl Plan workspace

list_workspace_tags

Lists all tags used for task categorization

list_workspace_users

Lists all users with access to the workspace

update_timeline_task

Provide updates as a JSON object. Updates an existing timeline task

Example Prompts for Toggl Plan in LlamaIndex

Ready-to-use prompts you can give your LlamaIndex agent to start working with Toggl Plan immediately.

"List all active projects in Workspace 992211."

"Create a timeline task named 'Re-authenticate module' in Project 19332, workspace 992211."

Troubleshooting Toggl Plan MCP Server with LlamaIndex

Common issues when connecting Toggl Plan to LlamaIndex through the Vinkius, and how to resolve them.

BasicMCPClient not found

Install: pip install llama-index-tools-mcp

Toggl Plan + LlamaIndex FAQ

Common questions about integrating Toggl Plan MCP Server with LlamaIndex.

How does LlamaIndex connect to MCP servers?

Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.

Can I combine MCP tools with vector stores?

Yes. LlamaIndex agents can query Toggl Plan tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.