How to Use the Clockwise MCP in LlamaIndex

Q: Can LlamaIndex query past Clockwise calendar events semantically?

Yes. By indexing the output of getcalendarevents into a vector store, LlamaIndex allows semantic search over your entire history, letting you find past syncs without knowing the exact dates.

Q: How do I filter which Clockwise tools LlamaIndex can access?

You use the allowedtools filter in the McpToolSpec setup to restrict access to sensitive write tools like updatepreferences while keeping read-only tools active.

Q: Does this MCP Server support asynchronous execution in LlamaIndex?

Yes. You can call totoollistasync to load tools like getteamavailability asynchronously, preventing your query engine from blocking while fetching team schedules.

Q: How does LlamaIndex handle complex nested calendar data?

The server outputs structured JSON from gettimeinsights, which LlamaIndex parses into document nodes, making it easy to chunk and index for precise retrieval.

Q: Is my team's Clockwise availability data safe with LlamaIndex?

Absolutely. The team schedules and preferences fetched via getteamavailability are held in transient memory during query execution. No raw calendar blocks are cached or stored outside your designated secure vector index.

Index your calendar history with LlamaIndex to query focus trends and schedule meetings grounded in team availability data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clockwise MCP to LlamaIndex

Create your Vinkius account to connect Clockwise 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 Clockwise with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Calendar Metadata into LlamaIndex Vector Stores

Stop guessing how your team spends their time. Your LlamaIndex agent can run `get_meeting_analytics` to pull historical meeting data and index it directly into your vector database for semantic search. Users can then ask natural language questions like 'who did I spend the most time with last month?' and the agent queries the indexed `get_calendar_events` output to give a grounded answer without hallucinations.

Query Real-Time Team Availability

When building RAG pipelines, you often need context from live systems. This MCP Server lets your query engine pull fresh data using `get_team_availability` to answer scheduling questions on the fly. The agent combines this live availability with your stored documents to find the best time for a client kickoff, checking `get_current_user` to ensure the organizer's context is preserved.

Analyze Focus Trends Over Time

Use `get_time_insights` to extract structural arrays of deep work patterns. LlamaIndex indexes these insights, allowing you to track how focus blocks change before and after major product launches. If focus time drops below a threshold, the agent can look up `get_focus_time` to verify active limits and suggest changes to the team's shared calendar rules.

Setup guide

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

Yes. By indexing the output of `get_calendar_events` into a vector store, LlamaIndex allows semantic search over your entire history, letting you find past syncs without knowing the exact dates.

You use the allowed_tools filter in the McpToolSpec setup to restrict access to sensitive write tools like `update_preferences` while keeping read-only tools active.

Yes. You can call `to_tool_list_async` to load tools like `get_team_availability` asynchronously, preventing your query engine from blocking while fetching team schedules.

The server outputs structured JSON from `get_time_insights`, which LlamaIndex parses into document nodes, making it easy to chunk and index for precise retrieval.

Absolutely. The team schedules and preferences fetched via `get_team_availability` are held in transient memory during query execution. No raw calendar blocks are cached or stored outside your designated secure vector index.

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