How to Use the Worktile MCP in LangChain

Build multi-step workflows connecting Worktile actions into complex logic 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 Worktile MCP to LangChain

Create your Vinkius account to connect Worktile 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 Worktile with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automating Project Status Updates

Need to change tasks across multiple projects? You can first run `list_projects` to scope the work, then use `list_tasks` on specific projects. Finally, you'll call `update_task`, feeding it the ID and new status information gathered in previous steps.

Mapping Team Structure and Channels

Figure out who talks to whom? Start by calling `list_members` to get a roster of users. Then, use that list to inform which channels you should check with `list_channels`, ensuring your agent knows exactly where the conversation is happening.

Creating Tasks from Team Needs

The workflow starts when an agent identifies a need for work. It first gathers team context using `get_team_info`. Based on that, it determines what's needed and executes the action via `create_task`, completing the full cycle in one chain.

Setup guide

Set up Worktile 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 Worktile 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({
    "worktile-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 Worktile 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 Worktile. 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 Worktile 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 Worktile MCP in LangChain

LangChain treats every MCP tool call as a measurable step. You can build complex chains where getting project details via `get_project` directly informs the parameters for calling `update_task`. It’s all about sequential logic.

Absolutely. The framework supports multi-server aggregation, letting your agent query across different data sources. You can run a chain that iterates through results from `list_projects`, giving you broad coverage.

A typical flow involves querying available resources, like running `list_tasks` to check current status. The agent then decides if a change is necessary and executes that decision by calling `update_task`. It’s pure reasoning.

The stateless nature of the client is manageable. You'll use `client.session()` to hold persistent context, ensuring that data gathered from earlier steps—like a list of members—is available when you call subsequent tools.

It handles task status and project metadata. Specifically, the server lets your agent read and write to work items using `list_tasks`, `get_project`, and `update_task`.

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