How to Use the Weights & Biases MCP in CrewAI

Q: How do I find all available projects in Weights & Biases using CrewAI?

The team uses the listwandbprojects tool. This function gathers a full list of every W&B project name or ID associated with your account, giving the agents scope for their mission.

Q: Can I list all experiment runs in a specific W&B project with CrewAI?

Yes. The listprojectruns tool fetches every run ID from an entire W&B project. A dedicated agent can then process this list to summarize the overall experimental status.

Q: Does Weights & Biases support listing reports with CrewAI?

The listprojectreports tool pulls a list of saved analysis report names from any W&B project. This helps the crew confirm that all required documentation has been generated for sign-off.

Build specialized teams to monitor and analyze Weights & Biases data using CrewAI.

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 CrewAI

Create your Vinkius account to connect Weights & Biases to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Project Management Agent Workflow

An agent can first call `list_wandb_projects` to discover all projects within a W&B account. Following that, it uses `list_project_artifacts` and `list_project_reports` sequentially. This setup allows the crew to systematically inventory everything: which artifacts exist and what reports are available for review.

Experiment Monitoring Agent

The Experiment Monitor agent uses `list_project_runs` to gather all run IDs from a W&B project. It then passes specific IDs to the `get_run_details` tool. This sequence lets the crew build deep context on any single run, understanding its metrics and configuration without human intervention.

Optimization Agent Analysis

For optimization tasks, the agent calls `list_project_sweeps`. This function retrieves a list of hyperparameter search sweeps within a W&B project. The crew can then analyze these sweep results to determine optimal parameters, automating the research phase of your machine learning pipeline.

Setup guide

Set up Weights & Biases MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Weights & Biases tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Weights & Biases Analyst",
    goal="Access and analyze Weights & Biases data via MCP.",
    backstory="Expert analyst with direct Weights & Biases access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Weights & Biases transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Weights & Biases Analyst",
        goal="Access and analyze Weights & Biases data via MCP.",
        backstory="Expert analyst with direct Weights & Biases access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Weights & Biases transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

The team uses the `list_wandb_projects` tool. This function gathers a full list of every W&B project name or ID associated with your account, giving the agents scope for their mission.

The server handles structured metadata like artifact lists, run metrics, and project configurations. This focus on discrete records makes it perfect for multi-agent specialization.

Yes. The `list_project_runs` tool fetches every run ID from an entire W&B project. A dedicated agent can then process this list to summarize the overall experimental status.

The `list_project_reports` tool pulls a list of saved analysis report names from any W&B project. This helps the crew confirm that all required documentation has been generated for sign-off.

The server touches metadata like artifact names and project IDs. Since the crew is performing autonomous operations, make sure your permissions restrict access only to W&B projects critical for the current task.

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