How to Use the Clockwise MCP in LangChain

Q: Can I run Clockwise tools inside a LangChain LangGraph agent?

Yes. You can pass tools like getteamavailability directly to a LangGraph agent to let it make routing decisions based on who is online. The agent updates the graph state with the retrieved availability array.

Q: How do I trigger autopilot changes safely in a LangChain chain?

You use toggleautopilot within a supervised run where a human-in-the-loop approves the mutate action before the chain executes it. This prevents the agent from shifting meetings without a final nod.

Let your LangChain agents run multi-step scheduling chains to protect focus blocks and coordinate team syncs on autopilot.

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 LangChain

Create your Vinkius account to connect Clockwise to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Calendar Logic in LangChain Chains

LangChain agents can feed the output of `get_calendar_events` directly into a scheduling decision loop. Instead of manually writing API calls, your chain evaluates the existing events, checks if a meeting is dragging down the team, and decides whether to trigger an update. By using this MCP Server, your agent chains can run `get_team_availability` to find overlapping free slots and immediately schedule a sync. No human needs to sit there and verify if the slots are clear before moving to the next step in the graph.

Optimize Deep Work Blocks Dynamically

Your LangChain agent can dynamically guard engineering time by calling `get_focus_time` to inspect active deep work limits. If a priority meeting threatens to break up a solid four-hour block, the agent initiates a reschedule. The agent uses `toggle_autopilot` to safely shift flexible meetings around without breaking your team's concentration. It checks user settings with `get_preferences` first to make sure it respects individual working hour boundaries.

Track and Adjust Meeting Analytics via LangSmith

Monitor how your agent behaves during calendar shifts by tracing MCP execution in LangSmith. When the agent calls `get_meeting_analytics`, you see the exact payload passing through the chain, letting you debug why a meeting was flagged as low value. You can also track how the agent updates settings via `update_preferences` during different times of the sprint. It gives you a clear audit trail of how the LangChain chain is managing your team's time.

Setup guide

Set up Clockwise MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Clockwise tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "clockwise-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Clockwise transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

LangChain traces every tool call, meaning you can monitor exactly how many tokens `get_time_insights` uses. The payload is clean JSON, keeping token overhead minimal even when pulling dense calendar histories.

Yes. You can pass tools like `get_team_availability` directly to a LangGraph agent to let it make routing decisions based on who is online. The agent updates the graph state with the retrieved availability array.

It does. You can combine this Clockwise MCP Server with a database server inside a single MultiServerMCPClient to let your agent pull a client list and instantly check their calendar availability.

You use `toggle_autopilot` within a supervised run where a human-in-the-loop approves the mutate action before the chain executes it. This prevents the agent from shifting meetings without a final nod.

All calendar events and focus time configurations retrieved via `get_calendar_events` are processed in memory within the secure V8 sandbox. Your sensitive meeting metadata never trains public models, and the Vinkius gateway handles authorization token exchange securely.

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