How to Use the Comet ML MCP in CrewAI

Q: Can CrewAI agents filter Comet ML tools?

Use the toolfilter option to limit which agents have access to specific commands. This keeps your research agents from accidentally running destructive tasks.

Deploy a specialized agent crew to manage your Comet ML lifecycle with this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Comet ML MCP to CrewAI

Create your Vinkius account to connect Comet ML 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 Comet ML with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent Comet ML research

Assign a researcher agent to `list_experiments` while a moderator agent oversees the output. The crew shares memory to build a complete picture of your project limits. You avoid manual oversight by letting one agent monitor the logs and another respond to discrepancies.

Specialized experiment analysis

Use `get_experiment_metrics` as a tool for your analysis agent. It pulls numeric bounds directly from your runs to inform the crew's decisions. This setup allows for hierarchical execution. Your lead agent assigns the task, and the worker agent fetches the data.

Autonomous workspace monitoring

The crew calls `list_workspaces` to scan your Comet ML account for new runs. It acts as an automated auditor that flags deviations in your ML pipeline. You set the rules once and let the agents handle the rest. They work in sequence to keep your projects organized.

Setup guide

Set up Comet ML 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 Comet ML tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Comet ML 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="Comet ML Analyst",
        goal="Access and analyze Comet ML data via MCP.",
        backstory="Expert analyst with direct Comet ML access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Comet ML 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 Comet ML. 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 Comet ML 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 Comet ML MCP in CrewAI

Pass the server URL into your agent definition's mcps list. The agents will automatically see the available tools for accessing your ML data.

Use the tool_filter option to limit which agents have access to specific commands. This keeps your research agents from accidentally running destructive tasks.

The shared memory in your crew ensures all agents see the same experiment metrics. This prevents conflicting actions during multi-step runs.

Install the necessary packages and provide the server endpoint in your agent configuration. The setup supports standard transport types for easy integration.

The server uses ephemeral sessions that expire after your agent task finishes. Your experiment parameters are never logged or stored by the host, ensuring your model IP stays private.

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