How to Use the Weights & Biases MCP in LlamaIndex

Q: Can I search past experiment results using Weights & Biases and LlamaIndex?

Yes. By indexing the output of getrundetails, you create a searchable knowledge base where users can ask questions about historical metrics or configurations.

Q: How do I list projects using Weights & Biases and LlamaIndex?

The listwandbprojects tool provides the raw project names. LlamaIndex then indexes these names, allowing you to query knowledge about your overall W&B presence.

Q: Does Weights & Biases help index reports using LlamaIndex?

You can use listprojectreports and pass the resulting list of report names into LlamaIndex. This allows you to build a knowledge base around your analysis outputs.

Augment LlamaIndex with weights-biases-mcp for grounded, searchable AI knowledge.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing Run Details

The `get_run_details` tool provides full experiment information: metrics and configs. When you feed this output to LlamaIndex, it becomes a verifiable data point in your knowledge base. Your RAG application can then query past performance details by semantic meaning, not just matching keywords.

Searching Project Artifacts

Use `list_project_artifacts` to gather names of datasets or models. LlamaIndex indexes these artifact listings into a vector store. This means you can ask questions like, 'Which dataset was used in the Q3 model?' and get an answer grounded in actual W&B API data.

Querying Project Runs

The `list_project_runs` tool gives a list of all experiment runs. By indexing this output, your knowledge base retains the context of every past attempt. Developers build applications that query these historical records to find relevant configurations without needing exact run IDs.

Setup guide

Set up Weights & Biases 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 Weights & Biases 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 Weights & Biases tools.",
)
response = await agent.run("List recent Weights & Biases 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 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 LlamaIndex

LlamaIndex doesn't just call the API; it takes the output (like a list of project artifacts) and indexes it. This allows your agent to query the results semantically, avoiding hallucinations.

The server touches specific project metadata, such as artifact names (`list_project_artifacts`) and run IDs. The index stores these descriptive strings for retrieval.

Yes. By indexing the output of `get_run_details`, you create a searchable knowledge base where users can ask questions about historical metrics or configurations.

The `list_wandb_projects` tool provides the raw project names. LlamaIndex then indexes these names, allowing you to query knowledge about your overall W&B presence.

You can use `list_project_reports` and pass the resulting list of report names into LlamaIndex. This allows you to build a knowledge base around your analysis outputs.

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