How to Use the ONES MCP in LlamaIndex

Q: Can I run semantic search over ONES tasks using LlamaIndex?

Yes, you can index the output of listtasks into a vector store. This allows developers to search past tickets using natural language queries instead of strict keyword matching.

Q: How does LlamaIndex prevent hallucinations when querying ONES?

The pipeline uses gettaskdetails to pull ground-truth data directly from the API. By feeding this raw JSON into the context window, the model only answers using verified task records.

Q: Does LlamaIndex support async tool execution with this ONES MCP Server?

Yes, you can call totoollistasync to load the tools into your FunctionAgent. This enables rapid, parallel fetching of listprojects and listmembers during heavy index updates.

Q: Can I filter which ONES tools LlamaIndex can access?

You can use the allowedtools filter during initialization to restrict access. For example, you can expose listtasks for search while blocking updatetask to prevent accidental modifications to your MCP setup.

Q: How does the ONES LlamaIndex integration secure our task details?

Vinkius processes all gettaskdetails payloads in ephemeral, zero-trust sandboxes on our managed MCP platform. Your proprietary task descriptions and bug reports are never stored or used to train models.

Index ONES project data directly into LlamaIndex vector stores to query live R&D tasks and workflows with semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ONES MCP to LlamaIndex

Create your Vinkius account to connect ONES to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup ONES with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index Live ONES Tasks for Semantic Search

`list_tasks` feeds live project data directly into your LlamaIndex vector store for immediate indexing. Your LlamaIndex agent queries this index to find semantic patterns in past ONES technical tickets without running heavy SQL queries.

Query Complex Workflows with LlamaIndex RAG

`list_workflows` provides the raw state transition data that LlamaIndex indexes alongside your team's wiki pages using this MCP server. Instead of reading outdated documentation, developers ask the LlamaIndex agent how a bug moves through ONES transitions.

Synthesize Project Summaries on Demand

`get_project` retrieves high-level progress details that your LlamaIndex pipeline synthesizes into daily status reports. This setup avoids manual status reporting by automating the retrieval of ONES project health directly into the LlamaIndex store.

Setup guide

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

Yes, you can index the output of list_tasks into a vector store. This allows developers to search past tickets using natural language queries instead of strict keyword matching.

The pipeline uses get_task_details to pull ground-truth data directly from the API. By feeding this raw JSON into the context window, the model only answers using verified task records.

Yes, you can call to_tool_list_async to load the tools into your FunctionAgent. This enables rapid, parallel fetching of list_projects and list_members during heavy index updates.

You can use the allowed_tools filter during initialization to restrict access. For example, you can expose list_tasks for search while blocking update_task to prevent accidental modifications to your MCP setup.

Vinkius processes all get_task_details payloads in ephemeral, zero-trust sandboxes on our managed MCP platform. Your proprietary task descriptions and bug reports are never stored or used to train models.

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