How to Use the watsonx Discovery MCP in LlamaIndex

Q: Can I use watsonx Discovery with LlamaIndex for historical lookups?

Yes. By indexing the output from listdiscoverycollections and other metadata calls, you can query past configurations or document lists to find answers grounded in actual API data.

Ground your AI with indexed knowledge from watsonx Discovery using LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect watsonx Discovery MCP to LlamaIndex

Create your Vinkius account to connect watsonx Discovery 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 watsonx Discovery with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Searchable Knowledge Bases

LlamaIndex doesn't just run a query; it indexes the results. The output from tools like `list_collection_documents` or metadata retrieved by `get_document_details` immediately become searchable knowledge chunks. This means you can build RAG applications where live API data and configuration details are combined into one unified, queryable index for semantic search.

Analyze Data Context & Scope

Want to understand the scope of a project? You use `list_discovery_collections` first. Then, if you need specifics on enrichment models, calling `list_available_enrichments` provides context. This structured data is indexed alongside your documents, giving semantic answers about the system's architecture.

Execute and Index Complex Queries

The workflow starts with a query. You pass the collection ID and text to `query_discovery_content`. Crucially, LlamaIndex takes this raw search result and indexes it. This allows you to query past sessions or configurations against actual API data—not just relying on the LLM's memory.

Setup guide

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

LlamaIndex takes the structured outputs from the MCP Server and converts them into vector embeddings. The resulting data becomes part of your knowledge graph, enabling deep semantic search across API results.

Yes. By indexing the output from `list_discovery_collections` and other metadata calls, you can query past configurations or document lists to find answers grounded in actual API data.

The system indexes documents, collection IDs, component settings, and enrichment definitions. The core type being indexed is structured metadata derived from the MCP Server calls.

It's highly reliable. By forcing all tool outputs into a unified index, you eliminate hallucinations because every answer must be traceable back to an API call result or document metadata.

You can include multiple MCP Servers by setting up the necessary connections in your basic client setup. This allows you to combine data from several sources into one master, queryable index.

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