Skip to content
Back to search

productops

MarketplaceWorks with Claude CodeGitHub

Your local MCP server that help you hold Jira and work easier

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/eugeneneverov--productops-mcp/badge.svg)](/listings/eugeneneverov--productops-mcp)

HTML

<a href="/listings/eugeneneverov--productops-mcp"><img src="/api/listings/eugeneneverov--productops-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Both servers run locally over stdio and need Node.js 20 or newer. Neither needs an account to try: each ships demo data.

**Claude Code**

claude mcp add productops-prioritization -- npx -y @productops-mcp/prioritization
claude mcp add productops-jira -- npx -y @productops-mcp/jira

**Claude Code plugin** (both servers and both skills in one install):

/plugin install productops --marketplace eugeneneverov/productops-mcp

On Claude Code older than 2.1.275: `/plugin marketplace add EugeneNeverov/productops-mcp`, then `/plugin install productops@productops`. Details in [plugin/README.md](plugin/README.md).

**Claude Desktop**: download `productops-prioritization-<version>.mcpb` or `productops-jira-<version>.mcpb` from the [latest release](https://github.com/EugeneNeverov/productops-mcp/releases/latest) and open it, or add the servers to the config as below.

**Any MCP client** (Claude Desktop, LM Studio, Cursor and others):

{
  "mcpServers": {
    "productops-prioritization": {
      "command": "npx",
      "args": ["-y", "@productops-mcp/prioritization"],
      "env": { "PRODUCTOPS_DATA_DIR": "/path/to/your/backlogs" }
    },
    "productops-jira": {
      "command": "npx",
      "args": ["-y", "@productops-mcp/jira"]
    }
  }
}

Then ask: "Rank the demo backlog with RICE and WSJF and tell me where they disagree", or "How is the current sprint on the demo PAY board going?". To read your own Jira Cloud, run `npx -y @productops-mcp/jira login` once and set `PRODUCTOPS_JIRA_MODE=live` ([docs/jira-live.md](docs/jira-live.md)).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 20 lines
  1. {
  2. "name": "productops",
  3. "owner": {
  4. "name": "EugeneNeverov",
  5. "url": "https://github.com/EugeneNeverov"
  6. },
  7. "metadata": {
  8. "description": "ProductOps plugins for Claude: prioritization and Jira sprint health."
  9. },
  10. "plugins": [
  11. {
  12. "name": "productops",
  13. "source": "./plugin",
  14. "description": "Product prioritization (RICE, WSJF, capacity scenarios) and Jira sprint health audits. Numbers are computed by local MCP servers; Claude explains them.",
  15. "version": "0.2.0",
  16. "license": "Apache-2.0",
  17. "homepage": "https://github.com/EugeneNeverov/productops-mcp"
  18. }
  19. ]
  20. }
README.md · README · 100 lines
  1. # productops-mcp
  2. [![npm: prioritization](https://img.shields.io/npm/v/@productops-mcp/prioritization?label=%40productops-mcp%2Fprioritization)](https://www.npmjs.com/package/@productops-mcp/prioritization)
  3. [![npm: jira](https://img.shields.io/npm/v/@productops-mcp/jira?label=%40productops-mcp%2Fjira)](https://www.npmjs.com/package/@productops-mcp/jira)
  4. [![CI](https://github.com/EugeneNeverov/productops-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/EugeneNeverov/productops-mcp/actions/workflows/ci.yml)
  5. [![License: Apache-2.0](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE)
  6. Open-source Product Operations toolkit built on the Model Context Protocol: local prioritization (RICE, WSJF, capacity scenarios) and Jira sprint intelligence, plus reusable agent skills. Calculations are done by code; the model only explains the results.
  7. ![A sprint health audit on the bundled demo data](docs/assets/demo.gif)
  8. <sub>The tool result is the real output of `assess_sprint_health` on the synthetic demo sprint; the answer is an abridged version of the skill's [example report](skills/sprint-health-audit/examples/demo-report.md). Regenerate with `node scripts/demo/make-demo-gif.mjs`.</sub>
  9. ## Install
  10. Both servers run locally over stdio and need Node.js 20 or newer. Neither needs an account to try: each ships demo data.
  11. **Claude Code**
  12. ```sh
  13. claude mcp add productops-prioritization -- npx -y @productops-mcp/prioritization
  14. claude mcp add productops-jira -- npx -y @productops-mcp/jira
  15. ```
  16. **Claude Code plugin** (both servers and both skills in one install):
  17. ```
  18. /plugin install productops --marketplace eugeneneverov/productops-mcp
  19. ```
  20. On Claude Code older than 2.1.275: `/plugin marketplace add EugeneNeverov/productops-mcp`, then `/plugin install productops@productops`. Details in [plugin/README.md](plugin/README.md).
  21. **Claude Desktop**: download `productops-prioritization-<version>.mcpb` or `productops-jira-<version>.mcpb` from the [latest release](https://github.com/EugeneNeverov/productops-mcp/releases/latest) and open it, or add the servers to the config as below.
  22. **Any MCP client** (Claude Desktop, LM Studio, Cursor and others):
  23. ```json
  24. {
  25. "mcpServers": {
  26. "productops-prioritization": {
  27. "command": "npx",
  28. "args": ["-y", "@productops-mcp/prioritization"],
  29. "env": { "PRODUCTOPS_DATA_DIR": "/path/to/your/backlogs" }
  30. },
  31. "productops-jira": {
  32. "command": "npx",
  33. "args": ["-y", "@productops-mcp/jira"]
  34. }
  35. }
  36. }
  37. ```
  38. Then ask: "Rank the demo backlog with RICE and WSJF and tell me where they disagree", or "How is the current sprint on the demo PAY board going?". To read your own Jira Cloud, run `npx -y @productops-mcp/jira login` once and set `PRODUCTOPS_JIRA_MODE=live` ([docs/jira-live.md](docs/jira-live.md)).
  39. ## Packages
  40. | Package | What it is |
  41. | -------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
  42. | `@productops-mcp/core` | Shared schemas (`Meta`, `ToolError`), tool runtime, policy, config, stderr logger |
  43. | `@productops-mcp/prioritization` | Local MCP server (stdio), fully offline: `calculate_rice`, `calculate_wsjf`, `compare_initiatives`, `simulate_capacity`, `explain_ranking`, optional `triumvirate_brief` / `triumvirate_verdict` (three independent judges) |
  44. | `@productops-mcp/jira` | Read-only MCP server (stdio) for sprint health: `list_projects`, `get_sprint_issues`, `analyze_cycle_time`, `find_blockers`, `assess_sprint_health`. Ships a synthetic demo dataset; reads your Jira Cloud through the official Atlassian MCP server after `productops-jira login` ([docs/jira-live.md](docs/jira-live.md)) |
  45. ## Try it from a checkout
  46. After `pnpm install && pnpm build`, ask the server to rank the bundled demo backlog:
  47. ```sh
  48. pnpm client packages/mcp-prioritization/dist/bin.js calculate_rice '{"initiatives":{"kind":"demo"}}'
  49. ```
  50. And audit the demo team's sprint (synthetic Jira data, no account needed):
  51. ```sh
  52. pnpm client packages/mcp-jira/dist/bin.js assess_sprint_health '{"boardId":1}'
  53. ```
  54. Your own backlog goes in a CSV or JSON file inside an allowed folder: `PRODUCTOPS_DATA_DIR`, `./data`, or the folders in `productops.config.json`. The columns match the fields in [docs/algorithms.md](docs/algorithms.md); the sprint metrics are defined in [docs/metrics.md](docs/metrics.md). Sample outputs are in [examples/reports/demo](examples/reports/demo).
  55. ## Skills
  56. [`skills/roadmap-prioritization`](skills/roadmap-prioritization/SKILL.md) turns the tools into a recommendation a product manager can act on: what to take, what to defer, the trade-offs, where the methods disagree, and how to reproduce every number. It is also served as the MCP prompt `roadmap-prioritization`, so it works in clients without Agent Skills support, such as LM Studio. [`skills/sprint-health-audit`](skills/sprint-health-audit/SKILL.md) does the same for a sprint (MCP prompt `sprint-health-audit`). See [skills/README.md](skills/README.md) and an [example report](skills/roadmap-prioritization/examples/demo-report.md).
  57. Skill quality is measured by [evals](evals/README.md): 10 cases, deterministic checks (every number and id must come from a tool), and a runner for any OpenAI-compatible endpoint, LM Studio included.
  58. ## Development
  59. Requires Node.js ≥ 22.12 and pnpm 10 (`corepack enable`). Published packages run on Node ≥ 20.
  60. ```sh
  61. pnpm install
  62. pnpm test # build, then unit + e2e tests
  63. pnpm lint && pnpm format:check
  64. pnpm client # start the built server and call `ping` through a real MCP client
  65. ```
  66. To connect a client to your checkout instead of npm, see [examples/clients](examples/clients/README.md). Design decisions are recorded in [docs/decisions](docs/decisions). Releases are described in [docs/releasing.md](docs/releasing.md) and listed in [CHANGELOG.md](CHANGELOG.md).
  67. ## License
  68. Apache-2.0, see [LICENSE](LICENSE). This license covers the code in this repository only. Use of third-party APIs (Atlassian Jira, Google Analytics and others) is governed by those providers' own terms.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.