Can I see the exact prompt that caused a specific error?

Yes. Use the `query_requests` tool to fetch direct prompts and outputs from the proxy logs. You can filter by status or custom tags to find the exact interaction that needs debugging.

How do I track costs for a specific customer ID?

Ask your agent to `query_costs` and include your customer identity in the filter. Helicone maps costs per model and user, allowing you to see exactly how much each client is burning in LLM tokens.

Can my agent log human feedback into Helicone?

Absolutely. Use the `log_feedback` tool to inject offline Human-in-the-Loop verdicts or text critiques directly into Helicone's database, helping you refine your model's grounding over time.

Helicone (LLM Observability) MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Helicone (LLM Observability)
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Helicone (LLM Observability) through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Helicone (LLM Observability) Assistant",
            instructions=(
                "You help users interact with Helicone (LLM Observability). "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Helicone (LLM Observability)"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Helicone (LLM Observability) MCP Server

Connect your Helicone account to any AI agent and take full control of your LLM observability and gateway monitoring through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Helicone (LLM Observability) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Helicone (LLM Observability), another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Request Monitoring — Query deep proxy logs to inspect exact prompts and outputs sent to LLM APIs directly from your agent
Cost Analysis — Break down spending by model, user, or custom metadata properties to monitor your AI burn rate in real-time
Latency Optimization — Measure Time To First Token (TTFT) and pinpoint slowness caused by specific upstream LLM providers
Prompt Management — Access managed prompt versions and track iterative changes in your AI instruction logic natively
Session Tracing — Isolate and analyze multi-turn graph traces connecting consecutive LLM calls to debug complex agentic workflows
User Insights — Track precise LLM interactions based on Helicone tags and identify your most active human clients
Feedback & RLHF — Extract user critiques (Thumbs Up/Down) and log offline Human-in-the-Loop verdicts to improve model grounding

The Helicone (LLM Observability) MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Helicone (LLM Observability) to OpenAI Agents SDK via MCP

Follow these steps to integrate the Helicone (LLM Observability) MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Helicone (LLM Observability)

Why Use OpenAI Agents SDK with the Helicone (LLM Observability) MCP Server

OpenAI Agents SDK provides unique advantages when paired with Helicone (LLM Observability) through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Helicone (LLM Observability) + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Helicone (LLM Observability) MCP Server delivers measurable value.

Automated workflows: build agents that query Helicone (LLM Observability), process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Helicone (LLM Observability), another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Helicone (LLM Observability) tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Helicone (LLM Observability) to resolve tickets, look up records, and update statuses without human intervention

Helicone (LLM Observability) MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Helicone (LLM Observability) to OpenAI Agents SDK via MCP:

get_prompt_versions

Irreversibly vaporize explicit validations extracting rich Churn flags

list_properties

Identify precise active arrays spanning native Gateway auth

log_feedback

Identify precise active arrays spanning native Hold parsing

query_costs

Perform structural extraction of properties driving active Account logic

query_feedback

Inspect deep internal arrays mitigating specific Plan Math

query_latency

Provision a highly-available JSON Payload generating hard Customer bindings

query_prompts

Retrieve explicit Cloud logging tracing explicit Vault limits

query_requests

Identify bounded CRM records inside the Headless Helicone Platform

query_sessions

Enumerate explicitly attached structured rules exporting active Billing

query_users

Dispatch an automated validation check routing explicit Gateway history

Example Prompts for Helicone (LLM Observability) in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Helicone (LLM Observability) immediately.

"How much did we spend on GPT-4o yesterday?"

"Show me the 10 slowest requests from the last hour"

"List all versions for the 'customer-service-bot' prompt"

Troubleshooting Helicone (LLM Observability) MCP Server with OpenAI Agents SDK

Common issues when connecting Helicone (LLM Observability) to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Helicone (LLM Observability) + OpenAI Agents SDK FAQ

Common questions about integrating Helicone (LLM Observability) MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.