debug-pipeline

Name: debug-pipeline
Availability: InStock
Author: Harness

Diagnose Harness pipeline executions and generate structured failure analysis via MCP.

80|16|Updated Mar 11, 2026

Search Tags:#logs #MCP #debug #pipeline #execution #diagnose #diagnostic-report

Ready to run

npx skills add https://github.com/harness/harness-skills --skill debug-pipeline-harness

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: debug-pipeline
Source: https://github.com/harness/harness-skills/tree/main/skills/debug-pipeline
Command: npx skills add https://github.com/harness/harness-skills --skill debug-pipeline-harness

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Diagnose Harness pipeline executions via MCP to produce structured, actionable reports detailing stage/step breakdowns, timing, bottlenecks, and failure details.

Core Features & Use Cases

Integrated diagnosis: Use harness_diagnose to fetch structured reports for a given pipeline or execution.
Deep dive mode: Request logs, YAML, and raw payloads for comprehensive analysis.
Context-aware health overview: Get project health data to spot trends and failures.

Quick Start

Provide an execution_id or pipeline_id to initiate a diagnostic scan and receive a formatted report.

Frequently Asked Questions about debug-pipeline

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I diagnose a failed Harness pipeline execution?▼

To diagnose a failed Harness pipeline execution, you provide an execution_id or pipeline_id to generate a structured report identifying bottlenecks, errors, and logs. This diagnostic scan applies to failed, successful, or in-progress runs.

What is included in a Harness pipeline diagnostic report?▼

A Harness pipeline diagnostic report includes stage and step breakdowns, execution timing, bottlenecks, and detailed failure information. You can also request logs, YAML definitions, and raw payloads for a comprehensive deep dive analysis.

How do I get pipeline execution logs using MCP?▼

You get pipeline execution logs by requesting a deep dive diagnosis through the harness_diagnose MCP tool. This fetches execution data, logs, and pipeline definitions to provide a comprehensive analysis of your pipeline run.

Do I need Harness MCP v2 to analyze pipeline failures?▼

Yes, you need Harness MCP v2 and the harness_diagnose tool to run the pipeline execution analysis. These dependencies are required to fetch the execution data, logs, and pipeline definitions needed for the diagnostic report.

Can I diagnose a pipeline that is currently in progress?▼

Yes, you can diagnose a pipeline that is currently in progress. The diagnostic scan applies to any Harness pipeline run, including failed, successful, or in-progress executions, to identify bottlenecks and errors.

What's the best way to spot trends in project pipeline failures?▼

The best way to spot trends in project pipeline failures is to use the context-aware health overview. This feature fetches project health data to help you identify recurring failures and trends across your Harness pipelines.