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

Q: How do I add Neptune.ai (ML Experiment Tracking) tools to a Mastra AI agent?

Instantiate the client using @mastra/mcp and pass the MCP Server URL. You then spread the tools into your agent's configuration, allowing it to call searchruns dynamically.

Q: Can Mastra AI trigger workflows based on Neptune.ai (ML Experiment Tracking) metrics?

Yes, you can design a workflow step that executes getattributes to check run parameters. If the metrics match your trigger conditions, the workflow moves to the next step.

Automate Neptune.ai (ML Experiment Tracking) audits with Mastra AI workflows and conditional branching.

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 Mastra AI

Create your Vinkius account to connect Neptune.ai (ML Experiment Tracking) to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate model checks with Mastra AI workflows

Build resilient MLOps pipelines using Mastra AI agents. By combining this MCP Server with Mastra's workflow engine, you can trigger automatic checks on model performance. The agent uses `list_models` to scan your registry and flags runs that fall below your accuracy thresholds. If a run fails the check, the workflow branches. The agent automatically calls `get_attributes` to pull the exact hyperparameters and logs them to your Slack or incident management tool without human intervention.

Resilient experiment search with auto-retries

Network hiccups shouldn't break your MLOps automation. Mastra's built-in exponential backoff ensures that calls to `search_runs` execute reliably even during API rate limits. Your agent can query massive project histories without failing mid-process. The agent uses `get_project` to target the right workspace before running queries. This structured execution prevents runaway API calls and keeps your automated reports consistent.

Human-in-the-loop workspace moderation

Prevent unauthorized changes or heavy queries in production workspaces. By using Mastra's tool approval features, you can require an engineer to approve calls to `get_user` or `list_projects` before they execute. This gives your team full control over who accesses sensitive project configurations. The agent queues the request, asks for approval, and then fetches the data once authorized.

Setup guide

Set up Neptune.ai (ML Experiment Tracking) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Neptune.ai (ML Experiment Tracking) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "neptuneai-ml-experiment-tracking-mcp-client",
  servers: {
    "neptuneai-ml-experiment-tracking-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Neptune.ai (ML Experiment Tracking) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Neptune.ai (ML Experiment Tracking) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Neptune.ai (ML Experiment Tracking) transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate the client using `@mastra/mcp` and pass the MCP Server URL. You then spread the tools into your agent's configuration, allowing it to call `search_runs` dynamically.

Yes, you can design a workflow step that executes `get_attributes` to check run parameters. If the metrics match your trigger conditions, the workflow moves to the next step.

Mastra's workflow engine handles rate limits natively with automatic retries. If `search_runs` returns a rate-limit error, the engine backs off and retries the call.

Yes, you can selectively register tools when setting up the MCP client. For instance, you can expose only `list_models` and restrict access to user credentials.

No, your ML experiment metrics and training parameters remain isolated. Vinkius executes the MCP tools in a zero-trust environment, passing the data directly to Mastra AI without caching.

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