How to Use the Harness MCP in Cursor

Q: How does the Harness MCP server work with Cursor's agent?

Once you configure the MCP server in your mcp.json file, Cursor's agent can call any of the 11 Harness tools. You can ask it to perform actions like executepipeline or fetch data with listprojects, and it will use the results to answer questions or generate code.

Q: What's the setup process for this Harness server in Cursor?

Create a file named .cursor/mcp.json in your project's root directory. Inside, you'll add an entry for the Harness MCP server, providing either the command for a local server or the URL for a remote one. Cursor will load the tools automatically on your next startup.

Inject live Harness pipeline and secret data directly into your code with Cursor's AI agent.

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 Cursor

Create your Vinkius account to connect Harness to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate Code with Live Harness Data

Stop writing boilerplate code against mock API data. Ask Cursor to write a script that interacts with your real CI/CD environment. For example: "Write a Python script to trigger the 'prod-deploy' pipeline and poll for completion." Your agent will use `list_pipelines` to get the correct ID, then generate working Python code that calls `execute_pipeline` and loops on `get_execution_status`. The code it writes isn't a generic template. It's populated with the actual identifiers for your pipelines, services, and environments. This means less time debugging and more time shipping code that works the first time.

Reference Infrastructure While You Code

Get infrastructure context without leaving your editor. Highlight a service name in your code, bring up the agent, and ask, "What secrets does this service have access to in staging?" Your agent uses `list_services`, `list_environments`, and `list_secrets` to find the answer and puts it right in the chat panel. This is a huge time-saver. You don't have to jump over to the Harness UI to look up connector details or available secrets. You stay in your flow state, get the information you need, and keep coding.

Run and Audit Deployments from the Editor

Your editor is now your mission control. Use the agent to kick off a deployment by typing, "Execute the 'rollback-database' pipeline." It uses the `execute_pipeline` tool to get it done. No web UI, no CLI commands to remember. After it runs, you can immediately check the results. Ask, "Show me the audit logs for that last pipeline execution." Your agent calls `get_audit_logs` and `get_execution_status` to pull a complete record of what happened. It’s the tightest feedback loop for managing your deployments.

Setup guide

Set up Harness MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Harness MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Harness transactions." If the MCP tools are loaded correctly, Cursor will call the Harness tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "harness-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

Once you configure the MCP server in your `mcp.json` file, Cursor's agent can call any of the 11 Harness tools. You can ask it to perform actions like `execute_pipeline` or fetch data with `list_projects`, and it will use the results to answer questions or generate code.

Absolutely. Just tell the agent which pipeline to run, for instance: "Run the 'api-staging-deploy' pipeline." The agent will use the `execute_pipeline` tool to start the job in Harness. You can then use `get_execution_status` to track its progress.

Ask the agent to get the status for a specific run. For example: "Show me the logs for the last failed execution of the 'payment-processor' pipeline." It will use `list_executions` and `get_execution_status` to find the run and display the relevant step details and logs.

Create a file named `.cursor/mcp.json` in your project's root directory. Inside, you'll add an entry for the Harness MCP server, providing either the command for a local server or the URL for a remote one. Cursor will load the tools automatically on your next startup.

Your Harness API key is stored in your local configuration and used by the MCP server to make authenticated calls. The server itself is ephemeral and stateless; it doesn't log or store your key, pipeline YAMLs, or any data from `get_audit_logs`. For project-based setups, make sure your `.cursor/mcp.json` file is included in your `.gitignore`.

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