How to Use the airfocus MCP in LlamaIndex

Q: How does LlamaIndex use the airfocus tools?

LlamaIndex wraps the MCP server's tools using McpToolSpec. This lets your agent not only call tools like getairfocusitem but also index their output. It's designed for building RAG applications on top of your live airfocus data.

Q: Can I build an index of just one airfocus workspace with LlamaIndex?

Yes. You can direct your agent to use listairfocusitems with a specific workspaceId. Your LlamaIndex application will then only ingest and index items from that single product roadmap.

Q: How do I get started with this MCP server and LlamaIndex?

Install llama-index-tools-mcp and point the BasicMCPClient to your Vinkius endpoint URL. The McpToolSpec will handle the rest. You can have a basic RAG agent querying your airfocus data in minutes.

Turn your airfocus roadmap into a queryable knowledge base for your LlamaIndex RAG apps. Ask questions, get answers from your data.

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 LlamaIndex

Create your Vinkius account to connect airfocus 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 airfocus with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Product Backlog

Use the airfocus tools from this MCP server to build a searchable index of your product strategy. LlamaIndex can call `list_airfocus_workspaces` and then `list_airfocus_items` to pull all your features, ideas, and tasks into a vector store. It turns your live roadmap into a knowledge source. Now you can ask questions in natural language. 'What features are we building for the mobile team?' The RAG application will query the index of your airfocus items to give you a grounded answer, complete with sources. No more manual searching.

Query Configurations and Custom Fields

This isn't just for items. You can index your workspace configurations, too. Use `list_airfocus_fields` to document all the custom fields, scoring criteria, and statuses you've set up across different products. This creates a 'memory' of your setup. When a new team member asks 'What does the 'strategic_fit' field mean?', your LlamaIndex app can pull the answer directly from the indexed data. It's perfect for onboarding and maintaining consistency.

Keep Your LlamaIndex Knowledge Base Fresh

Your roadmap changes daily. A LlamaIndex agent can be set up to periodically refresh its knowledge base. It will re-run `list_airfocus_items` to find new or updated items and ingest them automatically. You can even combine this with other tools. When an item is updated, the agent can use `get_airfocus_item` to fetch the full details and then trigger another action, like sending a summary to a Slack channel. Your agent keeps its RAG pipeline fed with live data.

Setup guide

Set up airfocus 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 airfocus 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 airfocus tools.",
)
response = await agent.run("List recent airfocus 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 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 LlamaIndex

LlamaIndex wraps the MCP server's tools using `McpToolSpec`. This lets your agent not only call tools like `get_airfocus_item` but also index their output. It's designed for building RAG applications on top of your live airfocus data.

Yes. You can direct your agent to use `list_airfocus_items` with a specific `workspaceId`. Your LlamaIndex application will then only ingest and index items from that single product roadmap.

Definitely. Once you've indexed your items, you can ask 'Tell me about the 'New Dashboard' feature'. The app will find the relevant item in its vector store and can even use `get_airfocus_item` to fetch the absolute latest details if needed.

Install `llama-index-tools-mcp` and point the `BasicMCPClient` to your Vinkius endpoint URL. The `McpToolSpec` will handle the rest. You can have a basic RAG agent querying your airfocus data in minutes.

Your agent will access and index data on your airfocus items, workspaces, and fields. Vinkius ensures this data is only processed within a secure, single-tenant environment for your session. Your API key is stored encrypted and is never exposed.

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