How to Use the Harness MCP in CrewAI

Q: Can CrewAI harness Harness for cross-project tasks?

Yes. Agents can call listprojects to discover work across your entire organization and coordinate deployments across multiple services.

Deploy autonomous DevOps crews with CrewAI to manage your Harness infrastructure without human oversight.

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 CrewAI

Create your Vinkius account to connect Harness to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous monitoring crews in CrewAI

Create a specialized monitor agent that constantly calls `list_executions` to check for health. It feeds this data to a second agent that decides if action is required. This moves your team beyond simple alerts. You get a system that identifies issues and prepares the environment for a fix before you even wake up.

Hierarchical deployment control

Use a lead agent to delegate tasks to worker agents based on project scope. The lead agent uses `list_projects` to map the work and `list_services` to find the right targets. This structure keeps your deployment logic organized. Each agent has a clear role, reducing the chance that an agent will try to do something outside its scope.

Audit trail generation

Let your agents generate their own compliance reports by querying `get_audit_logs`. They can summarize what they did and why they did it. This gives you a paper trail for every automated action. You can verify the agent's logic against your internal policies by reading the logs it collects.

Setup guide

Set up Harness MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Harness tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Harness Analyst",
    goal="Access and analyze Harness data via MCP.",
    backstory="Expert analyst with direct Harness access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Harness transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Harness Analyst",
        goal="Access and analyze Harness data via MCP.",
        backstory="Expert analyst with direct Harness access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Harness transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the server URL to your agent configuration. The agents will automatically discover the tools and use them to collaborate on your CI/CD tasks.

Yes. Agents can call `list_projects` to discover work across your entire organization and coordinate deployments across multiple services.

Yes. Assign a 'Compliance Agent' to the crew and give it access to `get_audit_logs`. It can monitor for unauthorized changes and report them back.

It does. You can connect using stdio, SSE, or HTTP, depending on how your crew is hosted. HTTP is usually the easiest for remote agents.

The server acts as a gateway with zero-trust principles. Only agents with your specific endpoint token can see your service definitions or pipeline YAML.

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