How to Use the watsonx Discovery MCP in LangChain

Q: Can I use watsonx Discovery with LangChain for RAG?

Absolutely. You can combine the search results from querydiscoverycontent with vector stores. Your agent handles retrieving the document list and then feeds those chunks into subsequent processing steps.

Build complex, multi-step reasoning chains using watsonx Discovery and LangChain.

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 LangChain

Create your Vinkius account to connect watsonx Discovery to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Multi-Step Reasoning Agents

The agent decides the whole sequence. You can build pipelines where one tool's output feeds directly into the next, guiding complex decisions. For instance, an agent first calls `list_discovery_collections` to narrow down scope, then uses `get_document_details` on a specific ID, and finally executes `query_discovery_content`. This chain allows for multi-stage reasoning.

Understand Data Structure & Health

Need to know what data you're playing with? The MCP Server lets your agent check the project's infrastructure. Use `list_available_enrichments` to see which NLP models (like Sentiment or Entities) are active, and `get_component_settings` for component health checks. This helps keep the chain running smoothly. It gives visibility into whether the underlying components are configured correctly before querying.

Targeted Content Retrieval

Don't just search everything; narrow it down first. You can list all available collections using `list_discovery_collections`. Then, you pinpoint specific documents with `list_collection_documents` before running a precise query via `query_discovery_content`. This methodical approach makes the agent more reliable and efficient when dealing with large datasets.

Setup guide

Set up watsonx Discovery MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes watsonx Discovery tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "watsonx-discovery-mcp": {
        "transport": "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,
    )
    result = await agent.ainvoke({
        "messages": "List recent watsonx Discovery transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

LangChain treats the MCP Server tools as callable functions. You wrap them into a chain, allowing your agent to select and sequence calls like `query_discovery_content` or `list_available_enrichments`. The result is actionable data that moves through the chain.

Absolutely. You can combine the search results from `query_discovery_content` with vector stores. Your agent handles retrieving the document list and then feeds those chunks into subsequent processing steps.

The server primarily handles metadata, configuration settings (via `get_component_settings`), and indexed documents. The results of these calls are the structured data passed through your chain.

Yes. Since the MCP Server defines specific, atomic tools, you get predictable inputs and outputs. This predictability is what makes building robust reasoning chains possible with watsonx Discovery.

The client supports multi-server aggregation. You can pass tool definitions from different sources into one agent, letting the LLM choose the right tool across all connected MCP Servers.

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