How to Use the Weights & Biases MCP in LangChain

Q: Can Weights & Biases help track historical runs using LangChain?

Yes. You can use listprojectruns to pull a list of all past experiments in a project. Then, your agent uses that ID with getrundetails to fetch the full metrics and config for deep analysis.

Q: What projects can I see using Weights & Biases and LangChain?

The listwandbprojects tool gives you a comprehensive view of all projects under your specific W&B entity. This is the starting point for any analysis chain.

Q: How do I list reports using Weights & Biases and LangChain?

You call listprojectreports to see every saved analysis report within a project. The output gives you the necessary names or IDs for your agent's next step.

Build complex ML pipelines with LangChain and weights-biases-mcp.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Weights & Biases MCP to LangChain

Create your Vinkius account to connect Weights & Biases 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 Weights & Biases with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Runs via MCP Server

The `get_run_details` tool pulls all the data you need for a specific run. You get summary metrics, full configurations, and everything attached to that experiment. This lets your agent analyze an existing result immediately. It's perfect for building chains where one step must check the performance of another.

List Project Artifacts

Need to know what assets live in a project? Use `list_project_artifacts` to get a list of everything saved, whether it's a dataset or a model. This data becomes available for subsequent steps in your chain. Your agent can check this inventory before deciding on the next action, making its reasoning much tighter.

View Project Sweeps

The `list_project_sweeps` tool finds all hyperparameter search attempts in a project. This is crucial for debugging which combination of settings actually worked best. Because your agent sees the list, it can intelligently decide whether to compare sweep results against run details before finalizing its recommendation.

Setup guide

Set up Weights & Biases 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 Weights & Biases 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({
    "weights-biases-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 Weights & Biases 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 Weights & Biases. 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 Weights & Biases 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 Weights & Biases MCP in LangChain

The MCP Server exposes W&B tools directly into your LangChain agent. This means the agent treats accessing W&B data like any other API call, building complex multi-step reasoning chains.

Yes. You can use `list_project_runs` to pull a list of all past experiments in a project. Then, your agent uses that ID with `get_run_details` to fetch the full metrics and config for deep analysis.

The server interacts with public project metadata, specifically listing artifact names (`list_project_artifacts`) and run IDs. It does not expose private credentials or raw compute outputs.

The `list_wandb_projects` tool gives you a comprehensive view of all projects under your specific W&B entity. This is the starting point for any analysis chain.

You call `list_project_reports` to see every saved analysis report within a project. The output gives you the necessary names or IDs for your agent's next step.

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