Eliminates Delivery Toil

Managing feature flags can be complex, especially across multiple projects and environments. Teams often need to navigate dashboards, APIs, and documentation to understand which flags exist, their configurations, and where they are deployed. What if you could handle these tasks using simple natural language prompts directly within your AI-powered IDE?Screenshot of the Claude Code interface displaying the output from a prompt to identify fully rolled-out feature flags that are safe to remove from code.Harness Model Context Protocol (MCP) tools make this possible. By integrating with Claude Code, Windsurf, Cursor, or VS Code, developers and product managers can discover projects, list feature flags, and inspect flag definitions, all without leaving their development environment.By using one of many AI-powered IDE agents, you can query your feature management data using natural language. They analyze your projects and flags to generate structured outputs that the agent can interpret to accurately answer questions and make recommendations for release planning.With these agents, non-technical stakeholders can query and understand feature flags without deeper technical expertise. This approach reduces context switching, lowers the learning curve, and enables teams to make faster, data-driven decisions about feature management and rollout.According to Harness and LeadDev’s survey of 500 engineering leaders in 2024: 82% of teams that are successful with feature management actively monitor system performance and user behavior at the feature level, and 78% prioritize risk mitigation and optimization when releasing new features.Harness MCP tools help teams address these priorities by enabling developers and release engineers to audit, compare, and inspect feature flags across projects and environments in real time, aligning with industry best practices for governance, risk mitigation, and operational visibility.Simplifying Feature Management WorkflowsTraditional feature flag management practices can present several challenges:Complexity: Understanding flag configurations and environment setups can be time-consuming. Context Switching: Teams frequently shift between dashboards, APIs, and documentation. Governance and Consistency: Ensuring flags are correctly configured across environments requires manual auditing.Harness MCP tools address these pain points by providing a conversational interface for interacting with your FME data, democratizing access to feature management insights across teams.How MCP Tools Work for Harness FMEThe FME MCP integration supports several capabilities: You can also generate quick summaries of flag configurations or compare flag settings across environments directly in Claude Code using natural language prompts.‍Some example prompts to get you started include the following:"List all feature flags in the `checkout-service` project." "Describe the rollout strategy and targeting rules for `enable_new_checkout`." "Compare the `enable_checkout_flow` flag between staging and production." "Show me all active flags in the `payment-service` project."  “Show me all environments defined for the `checkout-service` project.” “Identify all flags that are fully rolled out and safe to remove from code.”These prompts produce actionable insights in Claude Code (or your IDE of choice).Getting StartedTo start using Harness MCP tools for FME, ensure you have access to Claude Code and the Harness platform with FME enabled. Then, interact with the tools via natural language prompts to discover projects, explore flags, and inspect flag configurations.Installation & ConfigurationHarness MCP tools transform feature management into a conversational, AI-assisted workflow, making it easier to audit and manage your feature flags consistently across environments.PrerequisitesGo version 1.23 or later Claude Code (paid version) or another MCP-compatible AI tool Access to the Harness Platform with Feature Management & Experimentation (FME) enabled A Harness API key for authenticationBuild the MCP Server BinaryClone the Harness MCP Server GitHub repository. Build the binary from source. Copy the binary to a directory accessible by Claude Code.Configure Claude CodeOpen your Claude configuration file at `~/claude.json`. If it doesn’t exist already, you can create it. Add the Harness FME MCP server configuration:{
  ...
  "mcpServers": {
    "harness": {
      "command": "/path/to/harness-mcp-server",
      "args": [
        "stdio",
        "--toolsets=fme"
      ],
      "env": {
        "HARNESS_API_KEY": "your-api-key-here",
        "HARNESS_DEFAULT_ORG_ID": "your-org-id",
        "HARNESS_DEFAULT_PROJECT_ID": "your-project-id",
        "HARNESS_BASE_URL": "https://your-harness-instance.harness.io"
      }
    }
  }
}Save the file and restart Claude Code for the changes to take effect.To configure additional MCP-compatible AI tools like Windsurf, Cursor, or VS Code, see the Harness MCP Server documentation, which includes detailed setup instructions for all supported platforms.Verify InstallationOpen Claude Code (or the AI tool that you configured). Navigate to the Tools/MCP section. The Claude Code interface shows the Harness FME MCP server's status as connected, including the command path, arguments, configuration location, capabilities, and available tools.Verify Harness tools are available.The Claude Code interface displays the Harness FME MCP toolset, listing all available options.What’s NextFeature management at scale is a common operational challenge. With Harness MCP tools and AI-powered IDEs, teams can already discover, inspect, and summarize flag configurations conversationally, reducing context switching and speeding up audits. Looking ahead, this workflow extends itself towards a DevOps-focused approach, where developers and release engineers can prompt tools like Claude Code to identify inconsistencies or misconfigurations in feature flags across environments and take action to address them. By embedding these capabilities directly into the development workflow, feature management becomes more operational and code-aware, enabling teams to maintain governance and reliability in real time.For more information about the Harness MCP Server, see the Harness MCP Server documentation and the GitHub repository. If you’re brand new to Harness FME, sign up for a free trial today.

About ABC Fitness

At ABC Fitness Solutions, they keep the fitness industry moving forward. Their innovative software solutions empower fitness leaders to focus on what matters the most: building relationships and improving the lives of their club members. With their industry-leading payment processing and billing solutions, streamlined membership portals, and partnership services, the work ABC Fitness does is shaping the future of fitness. Their journey to being the primary SaaS solution for fitness clubs is made possible by the extremely passionate and talented professionals who propel their company and software solutions forward.

Jenkins? More like“Jankins”

Developers want to build things that either improve customers’ lives or improve other developers’ lives. The DevOps team at ABC Fitness didn’t have time for either. Engineers Chris Jowett and David Leonard instead spent a significant amount of time maintaining and troubleshooting Jenkins. 

ABC Fitness built its software deployment process using Jenkins and created a DevOps team to manage and administer the Jenkins pipelines. The DevOps team’s original goal was to increase deployment velocity and developer productivity, but that priority had to be shifted to keeping Jenkins from exploding. The DevOps team spent a month’s worth of work every quarter fixing broken pipelines and maintaining scripts. Jenkins pipeline failures began eroding developers’ deployment confidence.

Developers stopped trusting the CD process. Teams had a hard time differentiating between a pipeline failure and a code failure.

David Leonard | SRE DevOps Manager | ABC Fitness

David and Chris chased down defect after defect in Jenkins. At some point, Jenkins became the butt of a bad inside joke.

We referred to our Jenkins as "Jankins" because of its stability.

Chris Jowett | DevOps Architect | ABC Fitness

jan-ky | adjective |ˈjaNGkē | of extremely poor or unreliable quality. "the software is pretty janky"

ABC Fitness needed to find a better way to deliver code to customers.

Harness Relieves Deployment Burden

When ABC Fitness switched from Jenkins to Harness, they instantly reduced the troubleshooting and maintenance effort associated with software delivery. That effort has been refocused to improving the company’s platform.

We’ve been able to shift our focus to increasing velocity instead of maintaining antiquated procedures.

David Leonard |SRE DevOps Manager | ABC Fitness

Developers have regained confidence in the DevOps team by tracking deployment success with the metrics Harness provides. This confidence has led to a 20% increase in deployment velocity.

Most importantly, Harness has lifted a major burden from David and Chris’s shoulders.

Harness has paid for itself in time saved.

Chris Jowett | DevOps Architect | ABC Fitness