How to Use the Worksection MCP in LangChain

Q: What happens if I need to change user roles after listing them with Worksection and LangChain?

The agent can first use listallusers to check current users. It then uses this data, along with the target user's ID, to formulate a decision on which task tool—like completetask—to call next.

Q: Can I manage timers across multiple projects using Worksection and LangChain?

You can. An agent first calls listactivetimers to see what's running, and then uses the context of that timer along with project data from getprojectdetails to decide whether it needs to call stoptimer.

Worksection: Build multi-step project workflows with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Worksection MCP to LangChain

Create your Vinkius account to connect Worksection 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 Worksection with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Complex Project Planning via MCP Server

Your agent can figure out a whole project plan. It first calls `list_projects` to see what's available, then uses `get_project_details` to get the scope. The next step might be running `list_project_tasks` to check exactly which tasks are open.

Task and User Management with LangChain

Need to find who's on a team? The agent calls `list_all_users`, then uses the result to feed into `list_project_members` for specific context. You can build a chain that starts by calling `create_task` and finishes by assigning it using data from other tools.

Tracking Work History in Chains

The system tracks everything you do. It lets your agent call `list_work_history` to get an event log, which helps decide if it should use `get_task_details` or perhaps even run the `reopen_task` tool. The whole process is one continuous chain of thought.

Setup guide

Set up Worksection 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 Worksection 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({
    "worksection-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 Worksection 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 Worksection. 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 Worksection 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 Worksection MCP in LangChain

LangChain handles this by creating a reasoning pipeline that calls the MCP Server's tools. The output from `list_work_history` becomes the input for subsequent steps, allowing you to build complex queries over time.

Yep. You can design chains where one tool's output drives the next action. For example, finding a project ID via `list_projects` and then using that ID to call `get_project_details` in sequence.

The agent can first use `list_all_users` to check current users. It then uses this data, along with the target user's ID, to formulate a decision on which task tool—like `complete_task`—to call next.

You can. An agent first calls `list_active_timers` to see what's running, and then uses the context of that timer along with project data from `get_project_details` to decide whether it needs to call `stop_timer`.

It handles user profiles and task data. Specifically, the tools manage records derived from `list_all_users`, `get_task_details`, and `list_project_members`.

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