Product management over a shared product spine: link customer feedback and insights to features, tasks, sprints, releases and objectives; weekly signal memo; roadmap-drift detection; customer 360, funnel, path, retention, NPS and NRR analytics; artifact versioning and identity resolution. 38 tools, hosted remote server with OAuth 2.1 (DCR + PKCE).
Example client config (verify package name in the repo README)
{
"mcpServers": {
"claude-plugin": {
"command": "npx",
"args": ["-y", "claude-plugin"]
}
}
}Transparent heuristic — same formula for every entry. Total 55/100.
Triangulates HelpScout support tickets and ProductLift feature requests to generate prioritized product plans. Scores themes by convergence (same signal in both sources = 2x boost), scrubs PII, and accepts business metrics from other MCP servers via `kpi_context` for composable prioritization.
Polarion ALM integration with 24 read/write tools for documents, work items, traceability links, and comments. Renders documents as Markdown, searches with Lucene or SQL, walks incoming/outgoing links, and creates/updates/reorganizes work items. Every write tool supports `dry_run` with pre-write field, enum, and link-target validation. Requires Polarion 2506+. `uvx mcp-server-polarion`.
MCP server exposing the full Procore REST API (2,636 endpoints) for construction project management. Includes 7 discovery and execution tools covering projects, RFIs, submittals, daily logs, budgets, and more. Single-user OAuth with auto-refresh.
Software estimation server for AI agents: PERT, COCOMO II, Monte Carlo, sprint forecasting, token-to-time and cost mapping, and schedule-risk tools.
Turns pinned visual product feedback into an actionable backlog: list comments, read one with its target element's HTML, computed styles and screenshot, and update its status. Powers the [Loupe](https://mohamed-ashraf-elsaed.github.io/loupe/) SDK, browser extension, and `loupekit/laravel` package. Install `@loupekit/mcp` (binary `loupe-mcp`).
Reviews a plan for what's missing — unstated assumptions, omitted technical risks, and execution blind spots (a structured pre-mortem). `pip install road-poneglyph-mcp`