How to Use the Basecamp MCP in LangChain

Q: Can a LangChain chain create and assign a Basecamp task in one run?

Yes, you can chain these actions. The agent calls listpeople to find the correct assignee ID, then passes that ID directly to createtodo within the same execution loop.

Q: How does LangChain handle errors when a Basecamp project is missing?

If the MCP Server returns an error when getproject fails because an ID is incorrect, the LangChain agent catches the error. It then calls listprojects to find the correct ID and retry the operation automatically.

Q: Can I use LangChain to bulk-complete tasks?

You can write a loop where the agent calls listtodos to gather pending items, filters them based on your criteria, and calls completetodo on each matching task.

Run multi-step reasoning chains over your Basecamp projects and to-dos directly from your LangChain agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Basecamp MCP to LangChain

Create your Vinkius account to connect Basecamp 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 Basecamp with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Basecamp Project Setup in LangChain

The `create_project` tool initializes a fresh workspace with message boards and to-do sets ready to go. Your LangChain agent runs this first, grabs the project ID, and immediately passes it to `list_project_people` to see who is on the team. Instead of manual data entry, the output of one step feeds the next. The agent feeds the person IDs directly into `create_todo` to assign tasks without you writing a single line of glue code.

Trace Basecamp Todo Updates via LangChain MCP Server

The `update_todo` tool modifies existing tasks when deadlines shift or assignees change. Your LangChain agent monitors your chats or code updates, decides when to trigger this tool, and verifies the change with `get_todo`. Every single tool execution shows up in your LangSmith dashboard with exact latency and token counts. You see exactly why the agent decided to call `complete_todo` or reopen a task with `uncomplete_todo` during a complex run.

Automated Message Triaging and Commenting

The `list_messages` tool pulls the latest discussions from any project message board. Your LangChain agent reads these threads, processes the context, and uses `create_comment` to post updates or answers. By feeding message content into your chain, the agent identifies blockers. It can grab details using `get_message` and immediately draft a response back to the team.

Setup guide

Set up Basecamp 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 Basecamp 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({
    "basecamp-alternative-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 Basecamp 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 Basecamp. 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 Basecamp 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 Basecamp MCP in LangChain

You do not need to manage raw API keys in your code. Vinkius handles the authentication layer, giving your LangChain app a single endpoint token that securely connects to the Basecamp MCP Server.

Yes, you can chain these actions. The agent calls `list_people` to find the correct assignee ID, then passes that ID directly to `create_todo` within the same execution loop.

If the MCP Server returns an error when `get_project` fails because an ID is incorrect, the LangChain agent catches the error. It then calls `list_projects` to find the correct ID and retry the operation automatically.

You can write a loop where the agent calls `list_todos` to gather pending items, filters them based on your criteria, and calls `complete_todo` on each matching task.

Your project structures, to-do lists, and comment histories are completely isolated. Vinkius runs the MCP Server inside a secure V8 sandbox, ensuring your private team data never leaks to other tenants.

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