How to Use the Craft.io MCP in LangChain

Q: How do I get started with Craft.io and LangChain?

First, get your endpoint token from Vinkius. Then, use the MultiServerMCPClient in the langchain-mcp-adapters package to connect. Calling client.gettools() gives you a list of functions you can pass directly to a LangChain agent.

Q: Can my LangChain agent create new items in Craft.io?

Yes. The createitem tool lets your agent add new items to any workspace and portfolio you've configured. The agent can generate the title, description, and other fields based on the context from its chain.

Q: What's the best way to research competitors in Craft.io using LangChain?

Build a chain that starts with searchcompanies and getcompanycompetitors. Then, loop through the results and call getcompanynews and getcompanyfinancials for each. This gives your agent a rich dataset to reason about.

Build autonomous product agents in LangChain that research markets and update your Craft.io roadmaps.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Craft.io MCP to LangChain

Create your Vinkius account to connect Craft.io 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 Craft.io with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Your Market Landscape

Chain together a sequence of tool calls to get a full picture of the competition. Your LangChain agent can start with `search_companies` to find players in a new market, then automatically call `get_company_competitors` for each one. From there, it can dig deeper with `get_company_news` and `get_company_financials` to build a complete dossier. This isn't just a simple script. LangChain agents decide the next step based on what they find. If `get_company_news` reveals a funding round, your agent can decide to create a new task to analyze the impact. The output of one tool call becomes the input for the next, creating an intelligent research pipeline.

Automate Roadmap Management with a LangChain Agent

Give your agent the keys to your Craft.io workspace. It can `list_workspaces` to find the right area, `list_portfolios` to select a product line, and then use `create_item` to populate your backlog based on its research. This is how you connect your agent's findings to actual work. Your agent can take a high-level goal, break it down, and turn it into specific tasks in your roadmap. With this MCP Server, your agent isn't just thinking; it's doing the work right inside Craft.io. You see the results appear in your product plans instantly.

Build Custom Product Workflows

Create specific, targeted chains for your team's needs. You could build a workflow that periodically checks a key initiative using `get_item`. If the status changes, it can trigger another chain to pull fresh competitor data using `get_company` and `get_company_news` to provide updated context. LangChain's real strength is its composability. Combine these Craft.io tools with any of your other data sources—a database, a vector store, another API—all in the same chain. This lets you build a product intelligence system that fits your team's exact process.

Setup guide

Set up Craft.io 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 Craft.io 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({
    "craftio-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 Craft.io 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 Craft.io. 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 Craft.io 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 Craft.io MCP in LangChain

First, get your endpoint token from Vinkius. Then, use the `MultiServerMCPClient` in the `langchain-mcp-adapters` package to connect. Calling `client.get_tools()` gives you a list of functions you can pass directly to a LangChain agent.

Yes. The `create_item` tool lets your agent add new items to any workspace and portfolio you've configured. The agent can generate the title, description, and other fields based on the context from its chain.

Build a chain that starts with `search_companies` and `get_company_competitors`. Then, loop through the results and call `get_company_news` and `get_company_financials` for each. This gives your agent a rich dataset to reason about.

The MCP adapter will raise an exception in your chain. You can configure your agent with `handle_parsing_errors=True` to catch these and decide on a fallback action, like trying a different tool or asking for clarification.

Your Craft.io product plans, items, and company data are only accessed when a tool is called. Vinkius processes these calls in ephemeral, sandboxed environments that are destroyed after execution. Your Vinkius token is the only key; we handle the auth securely.

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