requirements-risk-analyser
Analyzes Jira tickets for requirement risks and can post risk reports as comments on Jira tickets.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Requirements Risk Analyser
An AI-powered requirements risk analysis pipeline built with TypeScript, Claude API, and MCP.
Finds gaps, ambiguities, and missing acceptance criteria in user stories and PRDs — before a single line of code is written.
Architecture
Three specialised agents run in sequence:
Agent 1 — Requirements Analyst: Extracts structured data from raw requirement text — acceptance criteria, user roles, business rules, third-party dependencies, integrations, and data fields
Agent 2 — Risk Identifier: Analyses the structured requirement against all business rules and acceptance criteria, identifies genuine gaps across 10 risk categories with HIGH / MEDIUM / LOW severity. Only flags risks that are missing from both AC and business rules combined
Agent 3 — Report Generator: Produces a quality score /100, a markdown risk report with a Sources Analysed section, and posts a comment on the Jira ticket if applicable
Related MCP server: BugForge
Input Sources
Three ways to provide requirements:
Method | How | What gets fetched |
File | Paste requirement into | File content only |
Jira | Pass | Jira description + linked Confluence pages + linked Jira tickets + attachments |
Inline | Pass text as CLI argument | Inline text only |
Jira + Confluence integration
When a Jira ticket is provided, the pipeline automatically:
Fetches the ticket description
Follows remote links to linked Confluence pages and fetches full page content
Fetches linked Jira tickets (parent / child / related) — 1 level deep
Downloads and reads plain text attachments
Merges all content into one combined requirement before analysis
Posts the risk report summary as a comment back on the Jira ticket
All sources fetched are listed in the Sources Analysed section of the report.
Risk Categories
Category | What it catches |
| No sad path defined |
| Ranges implied but not specified |
| Network/DB calls with no failure state |
| should, might, fast, valid, strong |
| Which user type does this apply to? |
| Business rule exists but no testable AC written for it |
| No auth, rate limiting, or input validation |
| Named external service with no fallback defined |
| External API assumed always available — no timeout/retry |
| PII collected with no compliance mention |
Sample Output
# Requirements Risk Report
**Requirement:** Password Reset
**Quality Score: 30/100** 🔴
## Risk Summary
| Severity | Count |
|----------|-------|
| 🔴 HIGH | 4 |
| 🟡 MEDIUM | 2 |
| 🟢 LOW | 0 |
## Sources Analysed
| Source | Type | Reference |
|--------|------|-----------|
| QRA-1 — User Password Reset | jira ticket | [Link](...) |
| Password Reset — Detailed Requirements | confluence page | [Link](...) |MCP Tools
analyse_requirement— full 3-agent pipeline (file or Jira input)extract_requirements— Agent 1 onlyidentify_risks— Agent 2 onlyget_risk_report— read last generated report
Tech Stack
TypeScript + Node.js
Anthropic Claude API (Sonnet 4.6 + Haiku 4.5)
Ollama (local LLM support — toggle via USE_OLLAMA)
Model Context Protocol (MCP) SDK
Jira REST API v3
Confluence REST API v1
Setup
git clone https://github.com/abchahal/requirements-risk-analyser.git
cd requirements-risk-analyser
npm install
cp .env.example .env
# Add your credentials to .envRunning the pipeline
Via terminal
# Analyse input/requirement.md
npm run pipeline
# Analyse a Jira ticket (fetches Confluence + linked tickets automatically)
npm run pipeline -- --jira PROJ-123
# Analyse inline text
npm run pipeline "As a user I want to reset my password..."Via Claude Desktop / Claude Code
Analyse the requirement in input/requirement.mdAnalyse Jira ticket QRA-1 for requirement risksOutput
output/
├── risk_report.md ← full risk report with score and sources
└── archive/
└── 2026-xx-xx/
└── risk_report.md ← previous runs archived automaticallyEach report includes:
Quality score /100 with colour indicator
Executive summary
Risks grouped by HIGH / MEDIUM / LOW severity
Suggested acceptance criteria in Given/When/Then format
Sources Analysed table — every URL fetched during analysis
Model Strategy
Agent | Model | Reason |
Agent 1 | Haiku 4.5 | Structured JSON extraction — fast and accurate |
Agent 2 | Sonnet 4.6 | Risk reasoning — requires deeper analysis |
Agent 3 | Haiku 4.5 | Report formatting — structured output |
MCP Setup via CLI
Step 1 — Update start-mcp.bat with your path
@echo off
cd /d "C:\path\to\requirements-risk-analyser"
node --loader ts-node/esm src/server.tsStep 2 — Register the MCP server
claude mcp add -s user requirements-risk-analyser "C:\path\to\requirements-risk-analyser\start-mcp.bat"Step 3 — Verify
claude mcp get requirements-risk-analyserExpected output:
requirements-risk-analyser:
Scope: User config (available in all your projects)
Status: ✔ Connected
Type: stdio
Command: C:\path\to\requirements-risk-analyser\start-mcp.batStep 4 — Remove the server (if needed)
claude mcp remove requirements-risk-analyser -s userSwitching between Ollama and Claude API
Ollama → Claude API
USE_OLLAMA=false
ANTHROPIC_API_KEY=sk-ant-your-key-hereClaude API → Ollama
ollama pull qwen2.5-coder:7bUSE_OLLAMA=true
OLLAMA_MODEL=qwen2.5-coder:7bRestart the MCP server after changing .env.
Provider comparison
Ollama (local) | Claude API (cloud) | |
Cost | Free | Per token |
Speed | 15–25 minutes | 30–60 seconds |
Quality | Good | Best |
Internet required | No | Yes |
Best for | Development and debugging | Production runs and demos |
Environment Variables
Variable | Required | Description |
| Yes (if USE_OLLAMA=false) | Anthropic API key from console.anthropic.com |
| Yes |
|
| No | Default: |
| No | Your Atlassian instance URL e.g. https://yourcompany.atlassian.net |
| No | Same as JIRA_BASE_URL on Atlassian Cloud |
| No | Your Atlassian account email |
| No | API token from id.atlassian.com/manage-profile/security/api-tokens |
Note: On Atlassian Cloud,
JIRA_BASE_URLandCONFLUENCE_BASE_URLare the same URL. The same API token works for both Jira and Confluence.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Spec-driven development for AI coding agents: live requirements, stories and traceability over MCP
AI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).
AI-native Day 0 modernization platform for PRDs, architecture, work orders, and code transformation.
Milestones, handoff tickets, project context, and deploy signals for AI-built apps over MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn AI-native specification framework that enables deep requirements analysis and structured project planning through intelligent Q\&A workflows. The MCP server provides tools for project initialization, requirement analysis, and the generation of living documentation like development plans and architecture specs.3 npmApache 2.0
- AlicenseNot gradedqualityDmaintenanceAI-powered QA defect reporting MCP server that generates Jira-ready defect reports with business context, reproduction steps, and priority from test scenarios and error details.26 npmMIT
- AlicenseNot gradedqualityDmaintenanceMCP server that provides project guardrails including prior art research, project status checks, next task retrieval, and quality gate enforcement for AI-assisted development.19 npmMIT
- FlicenseAqualityDmaintenanceAn intelligent MCP toolset for software testers that monitors code changes, analyzes test impact, recommends tests, and assesses risk, supporting multiple AI coding frameworks via dual transport modes.6-