How to Use the ClockShark MCP in LlamaIndex

Q: How do I use ClockShark tools with LlamaIndex?

Install the llama-index-tools-mcp package. You'll create a BasicMCPClient pointing to your Vinkius URL, wrap it in an McpToolSpec, and then call totoollistasync() to get tools for your agent.

Q: What's the best way to query ClockShark timesheets with LlamaIndex?

Set up a process to periodically fetch data with listtimesheets and index it. This creates a knowledge base you can query with natural language, like "show me all timesheets for John Doe from last week."

Turn live ClockShark data into a queryable knowledge base for your LlamaIndex RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ClockShark MCP to LlamaIndex

Create your Vinkius account to connect ClockShark 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 ClockShark with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index and Query Job Histories

This is more than just listing current projects. With LlamaIndex, you can periodically run `list_jobs` and `list_tasks`, then index the output into a vector store. Suddenly, you can ask plain-English questions like, "Which tasks were part of the downtown library renovation?" Your RAG app gets answers grounded in your actual ClockShark history, not guesswork. It turns a simple API into a searchable archive of all your project and task data.

Find Staff Based on Past Work

Build an expertise finder for your own team. Your LlamaIndex app can ingest data from `list_employees`, `list_timesheets`, and `list_tasks`, then vectorize it. When you need to staff a new job, you just ask your app a question. For example: "Find me an employee who has logged hours on HVAC tasks for the Miller account." It searches the indexed history of actual work performed and gives you a list of names, instantly.

Build Reports with Your MCP Server

Use this ClockShark MCP Server to feed a live data pipeline. Your agent can fetch fresh data using tools like `list_schedules` and `list_timesheets`. LlamaIndex then adds this information to a queryable index. This setup lets you build internal dashboards that answer complex operational questions without writing custom database queries. You're turning raw tool output into business intelligence that anyone on your team can query.

Setup guide

Set up ClockShark 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 ClockShark 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 ClockShark tools.",
)
response = await agent.run("List recent ClockShark 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 ClockShark. 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 ClockShark 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 ClockShark MCP in LlamaIndex

Install the `llama-index-tools-mcp` package. You'll create a `BasicMCPClient` pointing to your Vinkius URL, wrap it in an `McpToolSpec`, and then call `to_tool_list_async()` to get tools for your agent.

Yes, that's the primary use case. You can create an agent that calls `list_jobs` and `list_tasks`, then feeds the results directly into a LlamaIndex vector store for later retrieval and querying.

Set up a process to periodically fetch data with `list_timesheets` and index it. This creates a knowledge base you can query with natural language, like "show me all timesheets for John Doe from last week."

Your RAG app will use an agent equipped with the ClockShark tools. When a user asks a question, the agent can either query the indexed data for historical context or call a tool like `list_schedules` to get live data, then synthesize an answer.

Yes. Any access to your timesheet entries or job details is handled by Vinkius in a zero-trust environment. Each tool call runs in an isolated sandbox that is torn down immediately after, and no data is logged or retained by the platform.

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