How to Use the Craft.io MCP in LlamaIndex

Q: How does LlamaIndex index the output from Craft.io tools?

When you call a tool like listitems, the McpToolSpec converts the JSON output into Document objects. LlamaIndex then processes these documents and stores them as vectors in the index you've configured, making the content ready for semantic search.

Build a searchable knowledge base from your Craft.io roadmaps and market data, queryable with LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect Craft.io to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Product Strategy

Turn your roadmaps into a queryable knowledge base. Use the MCP tools to pull data from Craft.io—`list_workspaces`, `list_portfolios`, and `list_items`. LlamaIndex can automatically index the output, making your entire product plan searchable with natural language. Now you can ask your agent direct questions like, "What are the key items in the Q4 mobile portfolio?" LlamaIndex won't guess. It will retrieve the answer from the index it built from your `get_item` and `get_portfolio` tool calls, giving you grounded, accurate results.

Ground Your Agent in Live Market Data

Create a real-time market intelligence database. Your agent can run `search_companies`, `get_company_news`, and `get_company_competitors`, then feed all that output directly into a LlamaIndex vector store. Every piece of news and every new competitor becomes part of your agent's long-term memory. When you ask about a competitor later, the agent queries the indexed knowledge base for a fast, accurate answer based on the data it already collected. This makes your agent smarter over time without having to re-fetch data for every query. This is the core of a good RAG setup.

Your Craft.io MCP Server for RAG

This is where it all comes together. Ask a complex question like, "Summarize our main rival's recent product launches and list which of our Q4 items are affected." A LlamaIndex agent can query its indexed market data and its indexed roadmap data to synthesize a complete answer. This MCP Server provides the raw, structured data from Craft.io. LlamaIndex gives that data context and memory. You're building a system that understands the real relationship between your product plans (`get_item`) and the world outside (`get_company_news`).

Setup guide

Set up Craft.io MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Craft.io MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Craft.io tools.",
)
response = await agent.run("List recent Craft.io data")

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 LlamaIndex

When you call a tool like `list_items`, the `McpToolSpec` converts the JSON output into `Document` objects. LlamaIndex then processes these documents and stores them as vectors in the index you've configured, making the content ready for semantic search.

Yes, that's what it's designed for. You can index your own markdown files, PDFs, and other sources into the same LlamaIndex vector store. When you query it, the agent will pull context from both your documents and the live Craft.io data.

The index is a snapshot from when the tools were last called. For real-time data, you'd have your agent call the Craft.io tools directly. For analysis of past data, you query the index. A common pattern is to refresh the index on a schedule.

Build a 'Product Brain' agent. Index all your Craft.io items, portfolios, and workspaces. Then, you can ask it complex questions like 'What was the rationale for feature X?' and it can retrieve the original item description and related context.

The MCP Server only fetches the financial and company data you request. Vinkius manages authentication and runs each tool call in a separate, temporary sandbox. You control where the indexed data is stored, as that happens on your side within your LlamaIndex application.

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