How to Use the Harness MCP in Claude

Q: Can I see audit logs for my Harness account using Claude Desktop?

Yes. You can ask your agent to getauditlogs. For example, you could say, "Show me all audit logs from the last 24 hours related to 'production' secrets." This gives you a quick way to check for specific activity without manual searching.

Q: What's the difference between listsecrets and actually getting the secret value?

The listsecrets tool only shows you the names and metadata of the secrets in your Harness project. It does not expose the actual secret values. This lets your agent know what secrets are available without ever having access to the sensitive data itself.

Manage Harness CI/CD pipelines right from your Claude Desktop chat, from checking logs to triggering deploys.

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 Claude Desktop

Create your Vinkius account to connect Harness to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug Deployments Without Leaving Chat

Stop context switching just to check a build status. When a deployment fails, you can ask Claude Desktop, "What went wrong with the last production deploy?" and watch it work. Your agent uses `list_pipelines` to find the correct pipeline, `list_executions` to grab the most recent run, and then `get_execution_status` to pull the exact failed step and its logs. You get the answer right in your chat window. No more digging through the Harness UI. It's the fastest way to figure out what broke so you can get back to fixing it. You can even pull the full pipeline YAML with `get_pipeline` to see the configuration that failed.

Manage Projects and Environments

Get a quick overview of your entire setup without opening a browser tab. Ask your agent to `list_projects` to see everything you have access to in your Harness organization. From there, you can drill down into a specific project. Need to know where you can deploy a service? Just ask, "What environments are available for the 'api-gateway' project?" Your agent runs `list_environments` and gives you a clean list. It's a simple way to confirm deployment targets or check infrastructure connectors with `list_connectors` before you kick off a build.

Trigger Pipelines from a Prompt

Run your CI/CD pipelines with a simple sentence. Instead of navigating menus, just tell your agent: "Run the 'deploy-to-staging' pipeline." It finds the pipeline and uses `execute_pipeline` to start it immediately. This is perfect for repetitive tasks or rolling back a bad deployment quickly. Your agent can then monitor the job for you. A follow-up prompt like, "Is that deployment finished yet?" makes it call `get_execution_status` to give you a real-time update. This Harness MCP server turns your chat into a command center for your entire delivery process.

Setup guide

Set up Harness MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Harness MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Harness MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under harness-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 Claude Desktop

Just ask a direct question like, "Show me the last 5 executions for the 'frontend-deploy' pipeline." Your agent will use the `list_executions` tool to get the data from Harness and show you the status of each run right in the chat.

Yes. You can ask your agent to `get_audit_logs`. For example, you could say, "Show me all audit logs from the last 24 hours related to 'production' secrets." This gives you a quick way to check for specific activity without manual searching.

The `list_secrets` tool only shows you the names and metadata of the secrets in your Harness project. It does not expose the actual secret values. This lets your agent know what secrets are available without ever having access to the sensitive data itself.

If you're using the desktop app, you'll add the server command to your `claude_desktop_config.json` file. For the web version at claude.ai, you'll paste the remote server URL into the Custom Connectors section in your settings. The tools will appear in your chat input once connected.

Yes. The server only proxies requests to the Harness API using the token you provide. It doesn't store any of your data, like pipeline configurations from `get_pipeline` or secrets metadata from `list_secrets`. When using the local stdio connection with the desktop app, the process runs on your machine, so your data never even leaves your computer.

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