Craft.io MCP Server for LangChainGive LangChain instant access to 13 tools to Check Craft Status, Create Item, Get Company, and more
LangChain is the leading Python framework for composable LLM applications. Connect Craft.io through Vinkius and LangChain agents can call every tool natively. combine them with retrievers, memory, and output parsers for sophisticated AI pipelines.
Ask AI about this App Connector for LangChain
The Craft.io app connector for LangChain is a standout in the Productivity category — giving your AI agent 13 tools to work with, ready to go from day one.
Vinkius delivers Streamable HTTP and SSE to any MCP client
import asyncio
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MultiServerMCPClient({
"craftio": {
"transport": "streamable_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,
)
response = await agent.ainvoke({
"messages": [{
"role": "user",
"content": "Using Craft.io, show me what tools are available.",
}]
})
print(response["messages"][-1].content)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Craft.io MCP Server
Connect your Craft.io product management account to any AI agent and simplify how you coordinate your product strategy, manage features, and monitor roadmaps through natural conversation.
LangChain's ecosystem of 500+ components combines seamlessly with Craft.io through native MCP adapters. Connect 13 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.
What you can do
- Workspace Oversight — List all product management workspaces and retrieve detailed metadata and configurations.
- Feature & Epic Tracking — List, query, and create new items (features, stories, epics) within your workspaces to manage your backlog.
- Portfolio Control — List and query product portfolios to understand high-level organizational distribution and strategy.
- Data Insights — Fetch complete metadata, descriptions, and current status for any specific product item via AI.
- Roadmap Monitoring — Track the progress of features and epics directly from your agent to stay on top of your release cycle.
- Operational Visibility — Check account status and verify project metadata directly from Claude, Cursor, or any MCP client.
The Craft.io MCP Server exposes 13 tools through the Vinkius. Connect it to LangChain in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
All 13 Craft.io tools available for LangChain
When LangChain connects to Craft.io through Vinkius, your AI agent gets direct access to every tool listed below — spanning product-management, roadmap-software, feature-tracking, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.
Verify connectivity
Create an item
Get company details
Get competitors
Get company employees
Get company financials
Get company news
Get item details
Get portfolio details
List workspace items
List portfolios
List workspaces
Search companies
Connect Craft.io to LangChain via MCP
Follow these steps to wire Craft.io into LangChain. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.
Install dependencies
pip install langchain langchain-mcp-adapters langgraph langchain-openaiReplace the token
[YOUR_TOKEN_HERE] with your Vinkius tokenRun the agent
python agent.pyExplore tools
Why Use LangChain with the Craft.io MCP Server
LangChain provides unique advantages when paired with Craft.io through the Model Context Protocol.
The largest ecosystem of integrations, chains, and agents. combine Craft.io MCP tools with 500+ LangChain components
Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step
LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging
Memory and conversation persistence let agents maintain context across Craft.io queries for multi-turn workflows
Craft.io + LangChain Use Cases
Practical scenarios where LangChain combined with the Craft.io MCP Server delivers measurable value.
RAG with live data: combine Craft.io tool results with vector store retrievals for answers grounded in both real-time and historical data
Autonomous research agents: LangChain agents query Craft.io, synthesize findings, and generate comprehensive research reports
Multi-tool orchestration: chain Craft.io tools with web scrapers, databases, and calculators in a single agent run
Production monitoring: use LangSmith to trace every Craft.io tool call, measure latency, and optimize your agent's performance
Example Prompts for Craft.io in LangChain
Ready-to-use prompts you can give your LangChain agent to start working with Craft.io immediately.
"List all active workspaces in my Craft.io account."
"Show me the last 5 items in the 'Mobile App Roadmap' (ID: 10293)."
"Create a new feature: 'AI Search Integration' in workspace 'ws_88231'."
Troubleshooting Craft.io MCP Server with LangChain
Common issues when connecting Craft.io to LangChain through the Vinkius, and how to resolve them.
MultiServerMCPClient not found
pip install langchain-mcp-adaptersCraft.io + LangChain FAQ
Common questions about integrating Craft.io MCP Server with LangChain.
How does LangChain connect to MCP servers?
langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.