How to Use the airfocus MCP in LangChain

Q: What's the best way to manage airfocus priorities with LangChain?

Build a chain that uses listairfocusitems to get all items with their scores. Your agent can then reason about the data and use updateairfocusitem to change priorities or statuses based on your instructions. It's great for bulk updates.

Build LangChain agents that manage your airfocus roadmap, from creating items to updating priorities in a single chain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect airfocus MCP to LangChain

Create your Vinkius account to connect airfocus 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 airfocus with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Commands for Roadmap Management

Automate multi-step product tasks by linking airfocus tools together. Your LangChain agent can `list_airfocus_workspaces` to find the right product, then `list_airfocus_items` to review the backlog, and finally `get_airfocus_item` to pull the details of a specific feature before deciding what to do next. Each step informs the next one. This isn't just about running one command. It's about building a logical sequence. You can design a chain that finds duplicate feature requests, scores them based on custom fields fetched with `list_airfocus_fields`, and then flags one for an update using `update_airfocus_item`. The agent figures out the path.

Create and Update Features with LangChain

Let your agent add new ideas to your backlog directly. A simple prompt can trigger `create_airfocus_item`, turning a chat message into a structured feature in the correct workspace. No more context switching or manual data entry. Your agent can also handle maintenance. Give it a goal, like 'deprecate all features tagged Q1-2023', and it can use `list_airfocus_items` and `update_airfocus_item` in a loop to get the job done. It's a real time-saver for cleaning up the roadmap.

Full Observability with your MCP Server

Every tool call your agent makes is tracked. You see the exact inputs, outputs, and latency for every operation. This makes debugging your chains much simpler because you have a clear audit trail of the agent's reasoning. Connect it to LangSmith and you get a complete picture. You'll know precisely why your agent chose to `get_airfocus_item` instead of `list_airfocus_items`, and you can measure the token usage for each step. This isn't a black box.

Setup guide

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

You just need the Vinkius endpoint token for this MCP server. Use the `MultiServerMCPClient` in the `langchain-mcp-adapters` library, pass the tools to your agent, and it's ready to go. Authentication is handled for you.

Yes, as long as the API key you configured in Vinkius has permission. The agent can use `list_airfocus_workspaces` to see available options and then `create_airfocus_item` to add a new item to the specified workspace.

Build a chain that uses `list_airfocus_items` to get all items with their scores. Your agent can then reason about the data and use `update_airfocus_item` to change priorities or statuses based on your instructions. It's great for bulk updates.

Absolutely. The tools from this MCP server are standard LangChain tools. You can add them to any node in your graph, allowing for complex, cyclical reasoning about your product roadmap.

This server only interacts with your airfocus workspaces, items, and custom fields. All connections are made through Vinkius's ephemeral sandboxes, and your API keys are encrypted at rest. We never see your raw credentials.

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