> For the complete documentation index, see [llms.txt](https://developer.harness.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.harness.io/harness-ai/use-harness-ai.md).

# Use Harness AI

- [Overview of Harness AI](https://developer.harness.io/harness-ai/use-harness-ai/harness-ai.md): Learn about how AI improves your experience on the Harness platform.
- [Get Started](https://developer.harness.io/harness-ai/use-harness-ai/harness-create-with-ai.md): Use these example prompts to create pipelines, services, environments, connectors, and other Harness resources with Harness AI.
- [Effective prompting](https://developer.harness.io/harness-ai/use-harness-ai/harness-create-with-ai/effective-prompting-ai.md): Write effective prompts for Harness AI to generate pipelines, services, environments, and other resources.
- [Harness AI Chat use cases](https://developer.harness.io/harness-ai/use-harness-ai/harness-create-with-ai/harness-ai-chat-guide.md): Explore common use cases for Harness AI Chat across DevOps, security, cost management, reliability, and knowledge assistance.
- [Connect with AI](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai.md): Select and configure the right model connector for your Harness AI Worker Agents.
- [Anthropic Model Connector](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/anthropic-model-connector.md): Configure Claude access for Harness Worker Agents with API keys or AWS, GCP, and Azure cloud provider connectors, including IAM roles and OIDC.
- [OpenAI Model Connector](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/openai-model-connector.md): Configure OpenAI model access for Harness Worker Agents with API keys, AWS, GCP, or Azure cloud provider connectors, or LiteLLM endpoints
- [Anthropic Harness Connector](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/anthropic-harness-connector.md): Connect Harness to the Claude apps with the Anthropic Harness Connector so Claude can read and act on your pipelines, deployments, services, and costs using OAuth.
- [Harness MCP Server](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/index.md): Give AI agents full access to the Harness platform through 11 consolidated tools and 139 resource types using the Model Context Protocol (MCP).
- [Configure your AI client](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/index/configure-ai-clients.md): Add the Harness MCP Server to Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Gemini CLI, and Amazon Q Developer CLI using a Harness API key.
- [Harness Hosted MCP](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/index/hosted-mcp.md): Connect MCP-compatible clients to the Harness-managed MCP endpoint using OAuth through Harness ID, with no API key in your client configuration.
- [Self-hosted deployment](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/index/self-hosted-deployment.md): Run the Harness MCP Server with Docker, Kubernetes, or an MCP gateway, and serve multiple users over HTTP transport.
- [Environment variables reference](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/index/environment-variables.md): Full configuration reference for the Harness MCP Server, including identity, reliability, access control, logging, semantic search, and toolset filtering.
- [Tools reference](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/index/tools-reference.md): The 11 MCP tools exposed by the Harness MCP Server, with request examples, the pipeline run workflow, and MCP resource URIs.
- [Prompt templates](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/index/prompt-templates.md): The 27 pre-built Harness MCP Server prompt templates for DevOps, FinOps, DevSecOps, and Harness Code workflows.
- [Resource types](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/index/resource-types.md): All 139 Harness MCP Server resource types organized by toolset, with the CRUD operations and execute actions each one supports.
- [Approvals and safety](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/index/approvals-and-safety.md): How the Harness MCP Server confirms write operations through MCP elicitation, how risk-based auto-approve works, and which safeguards the server enforces.
- [Troubleshooting](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/index/troubleshooting.md): Resolve common Harness MCP Server errors and debug tool calls interactively with MCP Inspector.
- [MCP Connectors in Harness AI Chat](https://developer.harness.io/harness-ai/use-harness-ai/connect-with-ai/harness-ai-mcp-connectors.md): Add third-party MCP connectors to Harness AI chat to give the assistant tools from external services such as GitHub, GitLab, and Jira.
- [Context & Memory](https://developer.harness.io/harness-ai/use-harness-ai/context-and-memory.md)
- [Chat History and Memory](https://developer.harness.io/harness-ai/use-harness-ai/context-and-memory/memory-chat-history.md): Use Harness AI chat history and Memory to search past conversations and build on previous context.
- [Harness AI Memories](https://developer.harness.io/harness-ai/use-harness-ai/context-and-memory/harness-ai-memories.md): Use Harness AI Memories to personalize AI responses with context captured from your chats.
- [Core capabilities](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities.md): Harness AI brings intelligence to every stage of your software delivery lifecycle through three integrated capabilities.
- [In Harness UI](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-harness-ui.md)
- [Harness AI DevOps Agent](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-harness-ui/devops-agent.md): Create pipelines, manage resources, and troubleshoot with AI through natural language conversations in the Harness UI.
- [Optimize cloud costs using Harness AI](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-harness-ui/ccm-agent.md): Learn how to use Harness AI for cloud asset governance.
- [Fix security vulnerabilities using Harness AI](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-harness-ui/sto-agent.md): Enhanced remediation using Harness AI.
- [Troubleshoot builds and deployments with Harness AI](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-harness-ui/ci-agent.md): Troubleshoot builds and deployments with Harness AI.
- [Harness AI Support Agent](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-harness-ui/support-agent.md): Harness AI Support Agent provides instant answers to product and documentation questions.
- [In your IDE](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-your-ide.md)
- [Harness VS Code Extension](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-your-ide/vscode-extension.md): Install the Harness VS Code Extension to monitor pipelines, view logs, manage approvals, and use AI-assisted debugging directly in Visual Studio Code.
- [Harness AI Cursor Plugin](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-your-ide/cursor-plugin.md): Install the Harness AI plugin for Cursor to manage pipelines, debug deployments, and interact with Harness using natural language directly from your IDE.
- [Harness AI x Gemini CLI Extension](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-your-ide/harness-gemini-extension.md): Leverage Gemini CLI with Harness AI MCP Server to unleash your developer workflows.
- [In your pipelines](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-your-pipelines.md)
- [Worker Agent](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-your-pipelines/worker-agent.md): Create and configure AI-powered Worker Agents that run inside Harness pipelines to automate code review, incident response, data synthesis, and other intelligent workflows.
- [Agent permissions](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-your-pipelines/worker-agent/permissions.md): Configure Worker Agent permissions for manual and trigger-started pipelines through scoped tokens and RBAC.
- [Worker Agent configuration](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-your-pipelines/worker-agent/configuration.md): Configure Worker Agent instructions, MCP connectors, inputs, environment variables, triggers, and notifications.
- [Worker Agent examples](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-your-pipelines/worker-agent/example-agents.md): Explore Worker Agent examples including PR review, IaC plan safety, spec-driven development, and implementation agents.
- [Use Worker Agents in pipelines](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-your-pipelines/worker-agent/worker-agent-in-pipeline.md): Add Worker Agent steps to Harness pipelines, reference agent outputs, and gate deployments based on agent decisions.
- [Harness Agents reference](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-your-pipelines/worker-agent/harness-agents-references.md): Harness Agents Reference
- [Harness AI Release Agent](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-your-pipelines/release-agent.md): Learn how to release features confidently with data and feature operations like deploying, targeting, and managing flags with the Harness AI Release Agent.
- [In code](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-code.md)
- [AI-Powered PR Summaries and Code Review](https://developer.harness.io/harness-ai/use-harness-ai/core-capabilities/in-code/code-pr.md): Use Harness AI to generate pull request summaries, analyze code changes, and facilitate code review in Harness Code Repository.
- [Govern AI Output](https://developer.harness.io/harness-ai/use-harness-ai/govern-ai-output.md): Use Harness Skills, prompt templates that teach AI coding assistants how to generate pipeline YAML, manage resources, debug failures, and analyze costs on the Harness platform.
- [Skill Catalog](https://developer.harness.io/harness-ai/use-harness-ai/govern-ai-output/harness-skills.md): Browse the Harness Skills catalog, grouped by workflow mode, to find the right skill for creating, running, governing, or analyzing Harness resources.
- [Harness AI Rules](https://developer.harness.io/harness-ai/use-harness-ai/govern-ai-output/harness-ai-rules.md): Use Harness AI Rules to tailor AI output to enterprise standards before Harness resources are created or changed.
- [Workflows and reference](https://developer.harness.io/harness-ai/use-harness-ai/govern-ai-output/workflow-and-references.md): Chain Harness Skills into end-to-end workflows, and review skill file anatomy, MCP tools, and the harness-skills repository structure.
- [Release Updates](https://developer.harness.io/harness-ai/use-harness-ai/release-updates.md): Harness AI Release Updates