How to Use the Neptune.ai (ML Experiment Tracking) MCP in CrewAI

Q: How do I configure CrewAI agents to use Neptune.ai (ML Experiment Tracking)?

You pass the MCP Server URL directly into the agent's mcps parameter during initialization. The agent automatically discovers tools like searchruns and uses them as needed.

Q: Can a CrewAI analyst agent compare multiple Neptune.ai (ML Experiment Tracking) runs?

Yes, the analyst agent can execute searchruns to gather a list of runs, then loop through them using the MCP Server tools to compare hyperparameters and loss metrics.

Deploy specialized CrewAI agent teams to monitor and audit Neptune.ai (ML Experiment Tracking) runs autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Neptune.ai (ML Experiment Tracking) MCP to CrewAI

Create your Vinkius account to connect Neptune.ai (ML Experiment Tracking) 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 Neptune.ai (ML Experiment Tracking) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate CrewAI teams with the Neptune MCP Server

Deploy a crew of specialized agents to manage your experiments. One agent can use `search_runs` to find anomalous training sessions, while a second agent calls `get_attributes` to analyze the exact parameters that caused the failure. CrewAI's shared memory allows these agents to pass context directly. The auditing agent doesn't need to restart the search; it reads the run ID from the research agent's notes and goes straight to fetching the metrics.

Automated model registry monitoring

Keep your model registry clean without manual oversight. An autonomous monitoring agent can run on a schedule, calling `list_models` to check for untagged or outdated versions in your projects. Once identified, the moderator agent uses `get_project` to gather workspace details and alerts your engineering team. This prevents model drift and ensures your deployment pipeline stays accurate.

Hierarchical workspace discovery

Set up a manager agent to oversee your entire Neptune environment. The manager calls `list_projects` to map out active workspaces and delegates specific run investigations to subordinate agents. To maintain security, the manager agent can verify team access by querying `get_user` before delegating tasks. This keeps your autonomous operations secure and organized.

Setup guide

Set up Neptune.ai (ML Experiment Tracking) 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 Neptune.ai (ML Experiment Tracking) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Neptune.ai (ML Experiment Tracking) 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 Neptune.ai. 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 Neptune.ai (ML Experiment Tracking) 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 Neptune.ai (ML Experiment Tracking) MCP in CrewAI

You pass the MCP Server URL directly into the agent's `mcps` parameter during initialization. The agent automatically discovers tools like `search_runs` and uses them as needed.

Yes, the analyst agent can execute `search_runs` to gather a list of runs, then loop through them using the MCP Server tools to compare hyperparameters and loss metrics.

Agents use CrewAI's shared memory. When a researcher agent finds a run ID using `list_models`, the analyst agent reads that ID from the shared memory to fetch its attributes.

Yes, you can define a sequential crew where Agent A maps workspaces using `list_projects`, and Agent B inspects the active models inside those projects.

No, your ML training parameters and run metrics are fetched directly through the secure MCP connection. The Vinkius sandbox executes the requests ephemerally, ensuring no metadata is logged or stored outside your environment.

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