# ProductOps Jira Sprint Health

> ProductOps Jira Sprint Health is an open-source MCP server for productivity. Read-only MCP server that audits Jira sprint health, cycle time and blockers. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** CLI, API
- **Repository:** https://github.com/eugeneneverov/productops-mcp/tree/HEAD/packages/mcp-jira
- **MCP Registry name:** io.github.EugeneNeverov/productops-jira
- **Categories:** [productivity](https://ai-powered.com/categories/productivity), [health and science](https://ai-powered.com/categories/health-and-science)
- **Listing updated:** 2026-11-18

## About

The README says the server computes sprint metrics in code rather than letting a model estimate them, and that each finding links back to the specific issues behind it. Covered measures include cycle time, blocked and stale work, scope creep, carry-over and an overall health score.

It starts in fixtures mode with a bundled synthetic demo team, so it can be tried without any Jira account. Switching to live mode connects to a Jira Cloud site through the official Atlassian MCP server, after a one-time OAuth sign-in via the companion login command. The README notes that live calls may consume Rovo credits on the Atlassian plan.

It suits scrum masters, delivery leads and product managers who want a repeatable sprint review that an AI assistant can run and explain. Access is read-only, and paths for config, credentials and audit logs are configurable through environment variables.

## Features

- **Sprint health score:** Combines several checks into one health score with supporting findings.
- **Cycle time percentiles:** Reports cycle time percentiles and flags outlier issues.
- **Blocker detection:** Finds blocked and stale issues within a sprint.
- **Scope creep and carry-over:** Tracks work added mid-sprint and work rolled over to the next one.
- **Traceable findings:** Each finding points to the issues that produced it.
- **Demo mode included:** Ships synthetic team data so it runs without a Jira account.
- **Read-only access:** Reads Jira data without modifying issues or boards.

## Good for

- Run a sprint review audit with an AI assistant before planning
- Spot stale or blocked tickets across a team's current sprint
- Compare cycle time outliers to find process bottlenecks
- Test sprint health analysis on demo data before connecting Jira

## Install

### Claude Code (Terminal)

```sh
claude mcp add productops-jira -- npx -y @productops-mcp/jira
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "productops-jira": {
      "command": "npx",
      "args": [
        "-y",
        "@productops-mcp/jira"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "productops-jira": {
      "command": "npx",
      "args": [
        "-y",
        "@productops-mcp/jira"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "productops-jira": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@productops-mcp/jira"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "productops-jira": {
      "command": "npx",
      "args": [
        "-y",
        "@productops-mcp/jira"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "productops-jira": {
      "command": "npx",
      "args": [
        "-y",
        "@productops-mcp/jira"
      ]
    }
  }
}
```

## Tools

- `list_projects`: Projects and boards you can read
- `get_sprint_issues`: Issues of a sprint, normalized
- `analyze_cycle_time`: Cycle time percentiles and outliers
- `find_blockers`: Blocked and stale issues
- `assess_sprint_health`: Health score with findings (scope creep, WIP, carry-over and others)

## FAQ

### Does it need a Jira account to try?

No. The default fixtures mode uses bundled synthetic demo data, so no Jira account is needed.

### How does it connect to Jira Cloud?

In live mode it reads Jira Cloud through the official Atlassian MCP server, after running the login command. The README says sign-in uses OAuth with PKCE and no API token is stored.

### Can it change issues in Jira?

No. The README describes the server as read-only.

### What Node.js version is required?

Node.js 20 or newer. The response cache and audit log need 22.13 or newer.

### Is ProductOps Jira Sprint Health free?

Yes. ProductOps Jira Sprint Health is open source, so you can use and self-host it for free.

### How do I add ProductOps Jira Sprint Health to Claude Code?

Run this command in your terminal: claude mcp add productops-jira -- npx -y @productops-mcp/jira

### What are the best alternatives to ProductOps Jira Sprint Health?

The closest alternatives to ProductOps Jira Sprint Health are Agile Analytics MCP, Atlassian Extended, Orangescrum MCP Server, ProductOps Prioritization and BoardMark.

## Where this comes from

- Description: written from the project's README and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Agile Analytics MCP](https://ai-powered.com/mcp/agile-analytics-mcp): Agile Analytics MCP is a paid MCP server for cloud and infrastructure.
- [Atlassian Extended](https://ai-powered.com/mcp/atlassian-extended): Atlassian Extended is an open-source MCP server for developer tools.
- [Orangescrum MCP Server](https://ai-powered.com/mcp/orangescrum-mcp-server): Orangescrum MCP Server is an MCP server for productivity.
- [ProductOps Prioritization](https://ai-powered.com/mcp/productops-prioritization): ProductOps Prioritization is an open-source MCP server for productivity.
- [BoardMark](https://ai-powered.com/mcp/boardmark): BoardMark is a freemium MCP server for productivity.
- [Plith Rigor](https://ai-powered.com/mcp/plith-rigor): Plith Rigor is a freemium MCP server for productivity.

---
Source: https://ai-powered.com/mcp/productops-jira-sprint-health
