Provides project health auditing for Jira, including health scores, risk detection for overdue, unassigned, and reopened issues, and team workload analysis.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@jira-ai-auditor Audit project KAN"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Jira AI Auditor
Find the problems your Jira dashboard doesn't show you.
An MCP (Model Context Protocol) server that brings advanced project and sprint health auditing directly into Claude Desktop. Instantly detect overdue tasks, unassigned work, and reopened issues — with a proportional health score, risk scoring, and sprint-level analysis.
Why this tool
Most Jira integrations either give you full read/write access with no analysis, or a dashboard full of charts you still have to interpret yourself. This tool is different: it reads your project and tells you, in plain language, what's actually wrong — overdue tickets, unowned work, tasks that were marked done and quietly reopened.
It's also one of the few Jira tools that works correctly regardless of what language your team's workflow uses. Status detection is based on Jira's own language-independent status categories, not English text matching — so it works the same whether your statuses are named "Done", "Готово", or anything else.
Features 🆓 Free Project Health Score — proportional 0–100 score based on overdue, unassigned, and reopened work Overdue & Unassigned Detection — see exactly which tickets need attention Reopened Issue Detection — catches tickets marked Done and later reopened, using changelog history (not just current status) Risk Tags — each ticket flagged Low / Medium / High risk Team Workload View — how tasks are distributed across your team Works with any Jira language — tested with English and Russian workflows 5 free audits per day 💎 Premium Sprint Auditor (audit_sprint) — story points, completion rate, sprint-level risk assessment Exact Risk Scores — precise 0–100 score per ticket instead of a Low/Medium/High tag, factoring in priority, overdue duration, blocked status, and more Unlimited audits — no daily limit More advanced auditing features are on the roadmap Requirements Claude Desktop Node.js v18 or higher A Jira Cloud account with API access Installation
Clone the repository:
git clone https://github.com/Avtandil-abu/jira-ai-auditor cd jira-ai-auditor
Install dependencies:
npm install
Get your Jira API Token:
Go to Atlassian Account Settings Click Create API token Copy the token
Configure Claude Desktop:
Open your claude_desktop_config.json and add:
json { "mcpServers": { "jira-ai-auditor": { "command": "node", "args": ["/full/path/to/jira-ai-auditor/index.js"], "env": { "JIRA_DOMAIN": "https://your-domain.atlassian.net", "JIRA_EMAIL": "your-email@company.com", "JIRA_API_TOKEN": "your-api-token-here" } } } }
Restart Claude Desktop and start auditing:
Audit my Jira project KAN Usage
Once connected, simply ask Claude:
Audit project KAN What's the health score of my project? Find all overdue tasks in KAN Which tickets were reopened in KAN?
Sprint auditing (Premium only):
Audit the sprint for project KAN Upgrading to Premium
Premium unlocks unlimited audits, sprint auditing, and exact risk scores.
After checkout, you'll receive your Premium activation instructions by email within 24 hours.
Beta Program
We're looking for engineering managers and PMs to test this tool on real projects.
Support this project
If this tool is useful to you, a ⭐ on this repo genuinely helps — it's how other people find it.
👉 Support the development on Ko-fi
License
Proprietary — © 2026 Avtandil Labs. All rights reserved. See LICENSE.txt.
Enterprise-grade Jira project auditor. Analyzes project health, workload, and assigns smart Risk Scores to tasks.
| Name | Required | Description | Default |
|---|---|---|---|
| projectKey | Yes | Jira Project Key (e.g. 'KAN') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full behavioral burden. It does not disclose whether the tool is read-only or mutating, what permissions are needed, or what side effects occur; 'assigns smart Risk Scores' is ambiguous and could imply writes.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences and front-loads the core purpose. The phrase 'Enterprise-grade' is minor marketing fluff, but the rest is efficient and earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description is incomplete. It omits when to choose this over audit_sprint, behavioral safety details, and any expectations about output, leaving meaningful gaps for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the parameter is already fully documented in the schema. The description adds no additional meaning or format guidance for the projectKey parameter, making the baseline score of 3 appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb and resource: it audits Jira projects and analyzes health, workload, and risk scores. However, it does not explicitly distinguish itself from the sibling tool audit_sprint, leaving an agent to infer the project-vs-sprint distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use guidance, no exclusions, and no mention of the sibling tool audit_sprint. The agent is left to infer that this tool is for project-level audits rather than sprint-level audits.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
[Premium] Enterprise-grade Scrum Sprint Auditor. Predicts sprint success, analyzes velocity, story points, and risks. Requires an activated Premium license.
| Name | Required | Description | Default |
|---|---|---|---|
| projectKey | Yes | Jira Project Key (e.g. 'SCRUM') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It usefully discloses the Premium license requirement, which is a meaningful access constraint, but it does not state whether the tool is read-only, whether it mutates any data, or what its side effects are.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short and front-loads the purpose before the license requirement. It has minor redundancy in repeating the Premium status, and 'Enterprise-grade' is promotional filler, but overall it is efficient and well structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one fully documented parameter, and the description covers its general analytical purpose and license prerequisite. However, with no output schema and no annotations, the description omits return behavior, read-only status, and sibling differentiation, leaving clear gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single projectKey parameter, so the schema already documents the parameter fully. The description adds no additional parameter syntax or format details beyond what the schema provides, making 3 the correct baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb and resource: auditing a Scrum sprint, predicting success, and analyzing velocity, story points, and risks. It is clear what the tool does, but it never explicitly distinguishes itself from the sibling audit_project tool, leaving the agent to infer the sprint-vs-project scope difference.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states a prerequisite (requires an activated Premium license) and implies usage for sprint auditing, but it does not say when to choose this tool over audit_project or when not to use it. Guidance is present but minimal and does not resolve the sibling ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0audit_projectaudit_sprintScored across 2 tools
audit_project and audit_sprint target clearly distinct scopes (whole project vs. individual sprint), so an agent can always pick the right one. No overlapping purpose exists between the two tools.
Both names follow an identical verb_noun snake_case pattern (audit_*), directly mirroring the two domain objects. There is no deviation or mixed convention.
Two tools is thin for a server positioning itself as an enterprise-grade auditing suite; the surface feels narrow even for a deliberately focused auditor. It is not egregious, but it sits at the low end of usefulness.
Project-level and sprint-level auditing are covered, but obvious adjacent operations are absent — e.g. issue/task-level audit, backlog or board analysis, historical trend reporting, or exporting audit results. Agents will hit dead ends for anything outside those two scopes, and the 'Premium' gating on half the surface further narrows coverage.
Connect to Atlassian Jira, Confluence, Loom, and more to search, create, and manage your work.
Your audit methodology inside Claude: findings, risks, controls and workpapers in your team format.
Your Aurentia workspace — projects, CRM, tasks, deliverables — in Claude, Cursor or any MCP client.
Connect Claude to your Platform7n workspaces — chat, links, and tasks. One-click OAuth.