Harness
Access and interact with Harness platform data, including pipelines, repositories, logs, and artifact registries.
Ads
Overview
An MCP (Model Context Protocol) server that gives AI agents full access to the Harness.io platform through 11 consolidated tools and 240 resource types. Most MCP servers map one tool per API endpoint. For a platform as broad as Harness, that means 240+ tools — and LLMs get worse at tool selection as the count grows. Context windows fill up with schemas, and every new endpoint means new code. - 11 tools, 240 resource types. A registry-based dispatch system routes harness_list, harness_get, harness_create, etc. to any Harness resource — pipelines, services, environments, orgs, projects, feature flags, cost data, and more. The LLM picks from 11 tools instead of hundreds. - Full platform coverage. 39 default toolsets spanning CI/CD, GitOps, Feature Flags, Cloud Cost Management, Security Testing, Chaos Engineering, Database DevOps, Internal Developer Portal, Software Supply Chain, Infrastructure as Code Management, Release Management, Governance, Service Overrides, Knowledge Graph, and more
Installation
npm install -g harness-mcp-v2
Configuration
{
"mcpServers": {
"harness-prod1-mcp": {
"url": "https://mcp.harness.io/mcp",
"auth": {
"CLIENT_ID": "mcp-client"
}
}Capabilities
- List and inspect resources
Ask to `harness_list` or `harness_get` any of 240+ resource types, from pipelines and services to feature flags and cost data.
- Cross-project execution monitoring
Have the agent discover orgs/projects dynamically and report failed executions across your entire account hierarchy.
- Build and deploy end-to-end
Use built-in prompt templates to guide the full workflow, from code commit through pipeline deployment and verification.
- Debug failed pipelines
Leverage pre-built prompts to analyze execution logs, identify failure points, and suggest remediation steps.
- Review DORA metrics and vulnerabilities
Ask for performance insights or security triage using the included prompt templates for these specific workflows.
- Plan and manage feature flag rollouts
Use the dedicated prompt template to design, execute, and monitor progressive feature flag deployments.
Tags
- devops
- deployment
- monitoring
- cloud-infrastructure
Related MCP servers
Context7 MCP
OfficialOfficial Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.
Chrome DevTools MCP
OfficialOfficial Chrome DevTools MCP server for controlling and inspecting a live Chrome browser from coding agents such as Gemini, Claude, Cursor, and Copilot.
Mastra/mcp
OfficialClient implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.
GitHub MCP Server
OfficialConnect your AI assistant to GitHub repositories, issues, pull requests, and search.