How to Use the Helicone (LLM Observability) MCP in Mastra AI

Q: How do I configure Helicone (LLM Observability) with Mastra AI?

Install @mastra/mcp@latest. Instantiate a new MCPClient with your server URL, then call mcpClient.listTools() and spread them into your Mastra Agent's tool array. The framework auto-detects SSE or Streamable HTTP transports.

Q: Can Mastra AI trigger alerts based on Helicone (LLM Observability) latency?

Yes. You can build a workflow that calls querylatency on an interval. If the response times degrade, Mastra executes a conditional branch to page the on-call engineer.

Q: Does Helicone (LLM Observability) work with Mastra AI human-in-the-loop?

It does. You can enable requireToolApproval for sensitive actions. When the agent attempts to call getpromptversions to irreversibly vaporize explicit validations extracting rich Churn flags, a human must approve the step.

Q: How do I fetch metadata properties using this MCP Server?

The agent executes listproperties to identify precise active arrays spanning native Gateway auth. Mastra parses these properties and uses them to filter subsequent workflow steps.

Build resilient observability workflows in Mastra AI with the Helicone 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 Helicone (LLM Observability) MCP to Mastra AI

Create your Vinkius account to connect Helicone (LLM Observability) 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 Helicone (LLM Observability) with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Cost and Traffic Workflows

The `query_costs` tool performs structural extraction of properties driving active Account logic to trigger conditional Mastra AI workflows. If a specific user exceeds their token budget, your agent can catch the threshold and automatically pause their access. You can pair this with traffic analysis immediately. The `query_requests` tool identifies bounded CRM records inside the Headless Helicone Platform. Mastra evaluates these records and routes high-volume traffic alerts to your engineering team with built-in exponential backoff if the notification API fails.

Latency Monitoring and Feedback Loops

The `query_latency` tool provisions a highly-available JSON payload generating hard Customer bindings for your Mastra agents. When latency spikes above a defined limit, the workflow engine automatically retries the failing models or switches to a faster provider. To close the loop, `log_feedback` identifies precise active arrays spanning native Hold parsing. Mastra captures user satisfaction scores and uses `query_feedback` to inspect deep internal arrays mitigating specific Plan Math, adjusting routing logic based on actual human responses.

Auditing Users and Sessions via MCP Server

The `query_users` tool dispatches an automated validation check routing explicit Gateway history to audit suspicious activity. Your Mastra AI agent runs this step on a schedule, checking for anomalies in user behavior across your LLM endpoints. For deeper investigations, `query_sessions` enumerates explicitly attached structured rules exporting active Billing. Mastra compiles these session traces into a final report and deploys it to your cloud storage in a single command.

Setup guide

Set up Helicone (LLM Observability) 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 Helicone (LLM Observability) 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: "helicone-llm-observability-mcp-client",
  servers: {
    "helicone-llm-observability-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Helicone (LLM Observability) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Helicone (LLM Observability) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Helicone (LLM Observability) 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 Helicone. 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 Helicone (LLM Observability) 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 Helicone (LLM Observability) MCP in Mastra AI

Install `@mastra/mcp@latest`. Instantiate a new `MCPClient` with your server URL, then call `mcpClient.listTools()` and spread them into your Mastra Agent's tool array. The framework auto-detects SSE or Streamable HTTP transports.

Yes. You can build a workflow that calls `query_latency` on an interval. If the response times degrade, Mastra executes a conditional branch to page the on-call engineer.

It does. You can enable `requireToolApproval` for sensitive actions. When the agent attempts to call `get_prompt_versions` to irreversibly vaporize explicit validations extracting rich Churn flags, a human must approve the step.

The agent executes `list_properties` to identify precise active arrays spanning native Gateway auth. Mastra parses these properties and uses them to filter subsequent workflow steps.

The server handles explicit Cloud logging data and raw API queries. Mastra executes these tools inside the Vinkius zero-trust environment, ensuring that ephemeral session traces disappear the moment the workflow completes without writing to disk.

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