How to Use the Harness MCP in AutoGen

Q: How do I configure AutoGen with the Harness MCP Server?

Install autogen-extmcp. Initialize mcpservertools with your Streamable HTTP URL, then pass the resulting tool list into your AssistantAgent constructor.

Q: Can AutoGen agents trigger Harness pipelines independently?

They do this if you grant them access to the executepipeline tool. You usually want to require a human-in-the-loop step before the final execution command fires.

Q: How do AutoGen agents handle Harness deployment failures?

They read the error output from getexecutionstatus and discuss the next move. One agent suggests a retry while another proposes reverting the commit.

Q: Do I need to format the API inputs manually?

No. The McpToolAdapter automatically converts the JSON schemas for tools like listservices into formats the LLM natively understands.

Give your AutoGen agents the MCP Server tools to debate, approve, and execute Harness deployments autonomously.

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 AutoGen

Create your Vinkius account to connect Harness to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate deployment approvals in AutoGen

A developer agent proposes a release to production using `list_environments`. A separate security agent reviews the target and either approves or blocks the action. They argue based on actual system state, not assumptions. Once they reach consensus, the execution agent calls `execute_pipeline` to push the code.

Multi-agent troubleshooting

When a build fails, one agent constantly polls `get_execution_status` while another pulls historical context via `list_executions`. They divide the diagnostic workload. The monitoring agent reports step failures into the shared chat. The senior engineer agent analyzes those logs and suggests a rollback strategy before things get worse.

Validate configurations with the MCP Server

The MCP Server allows your compliance agent to audit the deployment YAML via `get_pipeline` and verify credential mappings using `list_secrets`. If a junior agent tries to push a configuration that exposes a database password, the security agent catches it. The group refuses to proceed until the YAML is corrected.

Setup guide

Set up Harness MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Harness tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Harness_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Harness data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Harness_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Harness data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]`. Initialize `mcp_server_tools` with your Streamable HTTP URL, then pass the resulting tool list into your `AssistantAgent` constructor.

They do this if you grant them access to the `execute_pipeline` tool. You usually want to require a human-in-the-loop step before the final execution command fires.

They read the error output from `get_execution_status` and discuss the next move. One agent suggests a retry while another proposes reverting the commit.

No. The `McpToolAdapter` automatically converts the JSON schemas for tools like `list_services` into formats the LLM natively understands.

Vinkius acts strictly as a pass-through layer. When your agents query `list_secrets` metadata, the ephemeral container processes the API call and immediately purges all memory.

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