How to Use the IBM watsonx MCP in LangChain

Chain IBM watsonx model calls directly into your LangChain agents for deterministic multi-step reasoning pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBM watsonx MCP to LangChain

Create your Vinkius account to connect IBM watsonx 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 IBM watsonx with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain watsonx operations in LangChain

Connect `generate_chat` and `generate_text` directly to your LangChain agents to build complex reasoning chains. You define the sequence where the output of one tool feeds the next, allowing your agents to handle multi-turn logic without manual intervention. This MCP server exposes these endpoints as native tools, meaning LangSmith tracks every latency spike and token count automatically. You see exactly how your agent decides which model call to trigger next.

Manage watsonx model tuning status

Use `start_model_tuning` to initiate training jobs and track progress through `get_tuning_status` within your chain. You no longer need to jump between dashboards to check if your custom model is ready for inference. By integrating these lifecycle tools, your LangChain pipeline can gate deployment based on real-time tuning results. It keeps your model development cycle tightly coupled to your application logic.

Query watsonx project resources

Access your workspace data using `list_projects` and `list_prompts` to dynamically pull configuration into your agents. This allows for runtime selection of prompt templates based on the specific project context. Your agents can inspect available foundation models with `list_models` and pull specific requirements via `get_model_details`. This ensures your chain always uses the correct model version for the task at hand.

Setup guide

Set up IBM watsonx 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 IBM watsonx 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({
    "ibm-watsonx-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 IBM watsonx 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 IBM watsonx. 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 IBM watsonx 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 IBM watsonx MCP in LangChain

Install the necessary MCP adapters and initialize the client with your endpoint URL. Once connected, use the library to fetch the tool definitions and pass them directly into your agent constructor for immediate use.

LangChain manages tool execution, but you must implement your own retry logic or queuing strategy to stay within watsonx limits. Monitor your tool call frequency to avoid hitting the ceiling during high-volume production tasks.

Yes, because the server exposes standard MCP tools, every call is logged through your existing tracing infrastructure. You get full visibility into inputs and outputs for every model generation step.

You can pull existing templates from your account using the `list_prompts` tool. This allows your agent to load and execute pre-defined prompts rather than hardcoding them in your application logic.

Your data is transmitted directly from your client to the IBM cloud endpoints defined in the MCP configuration. We do not inspect or store your prompt payloads; security depends on the authentication token you provide at the server level.

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