How do I find my Harness API Key?

Log in to Harness, go to **My Profile** (bottom left), and select **API Keys**. You can generate either a Personal API Key or use a Service Account Token from there.

Where can I find my Account ID and Org ID?

The Account ID is visible in your browser's URL when logged in (e.g., `account/XYZ123`). The Organization ID is typically found in the project settings or sidebar (default is often 'default').

Can I trigger a pipeline execution via this integration?

Yes! Use the `execute_pipeline` tool by providing the project ID and pipeline ID. Harness will initiate the workflow immediately.

Is the integration secure for managing secrets?

Absolutely. The integration only lists the metadata of your secrets (like names and identifiers) through your API key. Your credentials are encrypted and stored securely in the Vinkius Cloud.

Harness MCP Server for OpenAI Agents SDK 11 tools — connect in under 2 minutes

Name: Harness
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 11 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Harness through the 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="Harness Assistant",
            instructions=(
                "You help users interact with Harness. "
                "You have access to 11 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Harness"
        )
        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 Harness MCP Server

Connect your Harness.io platform to any AI agent and take full control of your software delivery and CI/CD pipelines through natural conversation.

The OpenAI Agents SDK auto-discovers all 11 tools from Harness through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Harness, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Pipeline Management — List, inspect, and trigger pipeline executions across your projects.
Execution Monitoring — Get real-time status updates and step details for active deployments.
Project Oversight — Browse your organizational structure and list projects within specific organizations.
Secrets & Infrastructure — Access lists of secrets, connectors, and environments to ensure your infrastructure is correctly configured.
Audit & Compliance — Retrieve platform audit logs to monitor changes and ensure security standards.
Service Insights — List microservices and environments defined in your DevOps ecosystem.

The Harness MCP Server exposes 11 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 Harness to OpenAI Agents SDK via MCP

Follow these steps to integrate the Harness 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 11 tools from Harness

Why Use OpenAI Agents SDK with the Harness MCP Server

OpenAI Agents SDK provides unique advantages when paired with Harness 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

Harness + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Harness MCP Server delivers measurable value.

Automated workflows: build agents that query Harness, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Harness, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Harness tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Harness to resolve tickets, look up records, and update statuses without human intervention

Harness MCP Tools for OpenAI Agents SDK (11)

These 11 tools become available when you connect Harness to OpenAI Agents SDK via MCP:

execute_pipeline

Trigger the execution of a pipeline

get_audit_logs

Retrieve platform audit logs

get_execution_status

Get status and step details for a specific pipeline execution

get_pipeline

Get details and YAML for a specific pipeline

list_connectors

List infrastructure connectors (Git, Docker, K8s, etc.)

list_environments

List environments defined in a project

list_executions

List executions for a specific pipeline

list_pipelines

List pipelines within a specific project

list_projects

List all projects in the configured Harness organization

list_secrets

List secrets configured in a project

list_services

List services (microservices) defined in a project

Example Prompts for Harness in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Harness immediately.

"List all pipelines in project 'E-commerce App'."

"Execute the 'Production Deploy' pipeline for project ID app_502."

"Show the status of the latest execution for pipeline deploy_v1."

Troubleshooting Harness MCP Server with OpenAI Agents SDK

Common issues when connecting Harness 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.

Harness + OpenAI Agents SDK FAQ

Common questions about integrating Harness 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.