How to Use the Harness MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK run Harness rollbacks automatically?

Yes, by combining executepipeline with the OpenAI Agents SDK built-in guardrails. You can set strict rules to ensure the OpenAI agent only triggers Harness rollbacks under specific failure conditions.

Q: How does the OpenAI Agents SDK track Harness MCP tools?

Every tool call, from listpipelines to getexecutionstatus, is logged. You can view the full Harness input and output payloads directly in your OpenAI developer dashboard.

Q: What happens if a Harness pipeline execution fails during an OpenAI Agents SDK run?

The OpenAI agent uses getexecutionstatus to detect the pipeline failure. It can then fetch Harness getauditlogs to find the root cause or alert your DevOps team.

Q: How does this MCP server protect my Harness secrets and audit logs?

The server only exposes metadata via listsecrets and never the plaintext secret values. All Harness audit logs retrieved via getauditlogs are processed in an ephemeral sandbox, ensuring your OpenAI compliance history remains private.

Trigger and monitor Harness pipelines safely using the OpenAI Agents SDK with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Harness MCP to OpenAI Agents SDK

Create your Vinkius account to connect Harness to OpenAI Agents SDK 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 Harness with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Harness pipelines with OpenAI Agents SDK safety gates

The `execute_pipeline` tool exposed by this MCP server lets your OpenAI agent trigger Harness deployments, but production systems need strict runtime boundaries. The OpenAI Agents SDK applies built-in guardrails to evaluate the agent's intent before it calls the Harness API. This prevents accidental Harness rollouts by validating OpenAI agent inputs against your predefined safety policies. Once the run begins, the OpenAI agent uses `get_execution_status` to monitor the Harness deployment step-by-step. If a step fails, the OpenAI Agents SDK handles agent handoffs, passing Harness error logs to a specialized troubleshooting agent. You trace the entire Harness deployment interaction directly in your OpenAI dashboard.

Map environments and services for agent decisions

Active deployment targets become visible to your OpenAI agent through the `list_environments` tool over the MCP connection. Instead of hardcoding target IDs, the OpenAI agent queries active Harness environments to select the correct deployment target. This dynamic discovery prevents misconfigured Harness deployments to production environments. Your OpenAI agent coordinates these targets with microservices retrieved via `list_services`. By combining these tools, the OpenAI agent maps Harness dependencies on the fly. It verifies that the correct Harness service version goes to the designated environment without manual mapping.

Audit security configurations before deployment

Security checks are simple with `list_secrets` because it exposes Harness credential metadata to your OpenAI agent without leaking actual values. This keeps your credentials secure while letting the OpenAI agent verify that necessary Harness environment variables exist. It ensures Harness deployments don't fail due to missing keys. Before any execution, the OpenAI agent queries `list_connectors` to verify Harness Git and Kubernetes access. If a Harness connector is missing, the OpenAI agent halts the process. This pre-flight check saves Harness execution credits and prevents broken OpenAI deployment loops.

Setup guide

Set up Harness MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Harness tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Harness tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Harness tools and returns structured results. Copy the full example on the right to get started.

agent.py

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

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Harness Agent",
            instructions="You have access to Harness tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Harness. 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 Harness 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 Harness MCP in OpenAI Agents SDK

You configure the MCP server URL with your Harness API key. The OpenAI Agents SDK connects to this endpoint, keeping your Harness credentials hidden from the LLM.

Yes, by combining `execute_pipeline` with the OpenAI Agents SDK built-in guardrails. You can set strict rules to ensure the OpenAI agent only triggers Harness rollbacks under specific failure conditions.

Every tool call, from `list_pipelines` to `get_execution_status`, is logged. You can view the full Harness input and output payloads directly in your OpenAI developer dashboard.

The OpenAI agent uses `get_execution_status` to detect the pipeline failure. It can then fetch Harness `get_audit_logs` to find the root cause or alert your DevOps team.

The server only exposes metadata via `list_secrets` and never the plaintext secret values. All Harness audit logs retrieved via `get_audit_logs` are processed in an ephemeral sandbox, ensuring your OpenAI compliance history remains 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