How to Use the Tower MCP in LangChain

Q: How does Tower and LangChain handle project discovery?

You use the listprojects tool to pull all available projects. Your agent then treats that output as a variable, allowing it to feed those project IDs into other tools like gettaskdetails for deeper analysis.

Q: What kind of data can LangChain use with Tower for documentation?

Your agent can list document folders using listdocfolders. This output gives the client the structure and names of available documents within the project, which then become inputs for subsequent processing steps.

Build complex reasoning chains with LangChain and Tower MCP Server. Observability built-in.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tower MCP to LangChain

Create your Vinkius account to connect Tower 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 Tower with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Project Discovery

The `list_projects` tool gives you a list of all available projects. You can immediately pass those project IDs into the next step, like calling `get_task_details`, to pull specific information. This means your agent doesn't just call tools; it builds an entire workflow. It determines which project is needed first, then pulls tasks from that project list.

Track Task Changes

Need to adjust a task? Start by calling `get_task_details` to review the current state of a task. Once you confirm the data, your agent can invoke `update_task` using the precise inputs. This two-step process—read then write—is perfect for agents needing confirmation before making changes. It makes sure that only verified information gets passed along.

Map Team Structure

Use `list_members` to get a roster of everyone in the organization. After getting names, you can call `list_teams` to see which teams they belong to. Your agent combines these two calls to map out complex reporting structures. This capability allows your client to understand who works with whom without multiple manual queries.

Setup guide

Set up Tower 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 Tower 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({
    "tower-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 Tower 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 Tower. 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 Tower 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 Tower MCP in LangChain

You use the `list_projects` tool to pull all available projects. Your agent then treats that output as a variable, allowing it to feed those project IDs into other tools like `get_task_details` for deeper analysis.

Yes. Since the framework is built on chains, every tool call—whether it's using `update_task` or `create_task`—is a measurable link in your reasoning pipeline, giving you full visibility.

Your agent can list document folders using `list_doc_folders`. This output gives the client the structure and names of available documents within the project, which then become inputs for subsequent processing steps.

It does. The setup supports multi-server aggregation, so you aren't limited to just Tower. You can combine this data with vector stores and other APIs in the same chain.

The server handles Project IDs, Task Statuses, Team Names, and Member User IDs. Your agent can read these concrete identifiers and use them to build structured workflows.

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