How to Use the timeghost MCP in LangChain

Build LangChain agents that log your Microsoft 365 billable hours without leaving your workspace.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect timeghost MCP to LangChain

Create your Vinkius account to connect timeghost to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup timeghost with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate workspace access with LangChain

The `check_timeghost_status` tool verifies API connectivity before your pipeline runs. Your agent calls this first to ensure the Microsoft 365 connection is alive. Once verified, the agent runs `list_timeghost_workspaces` to target the correct workspace. It then maps active teams using `list_timeghost_members` to prevent bad assignments.

Map active client projects

The `list_timeghost_clients` tool pulls your master client directory to map active accounts. This ensures your agent assigns hours to the correct contracts and keeps your records clean. Next, the agent calls `list_timeghost_projects` to find active initiatives. If it needs budget parameters, it uses `get_timeghost_project` to fetch specific project details for your MCP toolchain.

Track granular tasks and entries

The `list_timeghost_tasks` tool gathers active work items to keep your LangChain chains locked onto real deliverables. Your agent then uses `get_timeghost_task` to inspect specific ticket details. To prevent duplicate submissions, the agent pulls recent logs with `list_timeghost_entries`. It can then inspect any single record using `get_timeghost_entry` to verify the accuracy of the logged hours.

Setup guide

Set up timeghost 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 timeghost 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({
    "timeghost-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 timeghost 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 timeghost. 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 timeghost 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 timeghost MCP in LangChain

It runs stateless by default, letting your chains pass workspace context dynamically. If you need to lock onto a specific Microsoft 365 tenant, you can initialize a persistent session in your client configuration.

Yes, you can. You convert the tools using the standard MCP adapter and feed them into your LangChain agent. The agent will decide when to log hours based on chat history.

The agent passes the required arguments directly through the tool call step in your chain. The model reads the schema and applies the filters automatically before calling the API.

No, Vinkius handles the authentication. Your agent uses a single secure token to interact with the API, bypassing OAuth headaches entirely.

Your time logs and workspace memberships never touch third-party databases. Vinkius runs the server in an isolated, ephemeral sandbox that destroys all memory traces the moment your request finishes.

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