How to Use the TrackingTime MCP in LlamaIndex

Q: How does LlamaIndex help me track time entries?

The system indexes the data returned by listtimeentries. This means you can search for specific dates or projects within your historical logs, making retrieval much faster than manual filtering.

Q: Can LlamaIndex list my current tasks?

Yes. It uses the output of listtasks and indexes it. This means you can ask complex questions about task dependencies or owners, pulling the answer from your indexed data set.

Q: What's the best way to use MCP Server with LlamaIndex?

You pass the tool specifications—like listcustomers and getuserprofile—to the FunctionAgent. This allows your RAG application to dynamically access real-time business data when answering user queries.

Q: Does TrackingTime support historical reporting with LlamaIndex?

Yes, because every time log is indexed after calling listtimeentries, you build a comprehensive history. You query the index for insights into resource allocation over long periods.

Q: What data types does this MCP Server touch regarding privacy?

This server touches project details (listprojects), customer lists (listcustomers), and user identification data (getuserprofile).

Index all time logs and projects with LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect TrackingTime MCP to LlamaIndex

Create your Vinkius account to connect TrackingTime to LlamaIndex 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 TrackingTime with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search project data via MCP Server

The `list_projects` tool gives you a list of everything you're working on. When LlamaIndex indexes the results, it doesn't just store text; it makes that project structure semantically searchable. You can then query past sessions to find specific projects mentioned in old data. This is huge for RAG applications. Instead of reading through dozens of reports, you ask a natural language question and get an answer grounded directly in your indexed `list_projects` output.

Grounding time entries with LlamaIndex

Need to know why a certain time was logged? The `add_time_entry` tool records the data, but indexing it means you can query *about* that entry later. You ask: 'What did I work on for Client X last month?' and the system searches through all recorded times. The output of `list_time_entries` becomes a searchable knowledge base. This is way better than just having a raw log file; it gives context.

Build task management pipelines with LlamaIndex

The agent uses `create_task` to record new work items, and then indexes the details of that task. This allows your knowledge base to contain not just documents, but executable state data—the tasks themselves. You can query for 'all pending marketing tasks' across history. This indexing capability is critical when combining live API calls with static documentation. Your LlamaIndex application reads both and gives you a unified answer.

Setup guide

Set up TrackingTime MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all TrackingTime MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

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

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to TrackingTime tools.",
)
response = await agent.run("List recent TrackingTime data")

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 TrackingTime. 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 TrackingTime 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 TrackingTime MCP in LlamaIndex

The system indexes the data returned by `list_time_entries`. This means you can search for specific dates or projects within your historical logs, making retrieval much faster than manual filtering.

Yes. It uses the output of `list_tasks` and indexes it. This means you can ask complex questions about task dependencies or owners, pulling the answer from your indexed data set.

You pass the tool specifications—like `list_customers` and `get_user_profile`—to the FunctionAgent. This allows your RAG application to dynamically access real-time business data when answering user queries.

Yes, because every time log is indexed after calling `list_time_entries`, you build a comprehensive history. You query the index for insights into resource allocation over long periods.

This server touches project details (`list_projects`), customer lists (`list_customers`), and user identification data (`get_user_profile`).

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