Official description๐ โ๏ธ - Combine Help Scout tickets and ProductLift feature requests into prioritized product plans, scoring themes by cross-source convergence and scrubbing PII.
Config template (adjust for your client)
claude mcp add pm-copilot -- npx -y pm-copilot
A pasteable skeleton generated from the repository name. Check the project README for the exact package and arguments.
Star count
30 โ ยท dkships/pm-copilot ยท read from the GitHub search API ยท (checked 2026-10-16 20:00:20)
Source
collected from the punkpeye/awesome-mcp-servers list ยท type: MCP server
Harvest history
first seen 2026-10-09 ยท last seen 2026-10-16 ยท seen 32ร ยท listed by 7 sources
Score
score 703 ยท 30 โ ยท 7 sources ยท mcp
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: MCP ๆๅก. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository dkships/pm-copilot๏ผfirst catalogued 2026-10-09๏ผlast seen 2026-10-16ใThere is no official certification or quality rating here โ we record sources and dates only.
An MCP server that triangulates customer support tickets, feature requests, and AI support agent conversations to help PMs decide what to build next. --- > **Real results:** Analyzed 3,353 signals in one 30-day window: 1,678 support tickets, 276 feature requests, and 1,399 AI support agent conversations across 4 products. > > The chats are signal a ticket-only analysis never sees. **Read the full story:** I built an MCP server that changed how I prioritize products --- What makes this different - **Signal triangulation.** Matches support tickets against feature requests to find convergent themes, and gives convergent themes a 2x priority boost. - **The deflection blind spot.** An AI support agent answers questions that never become tickets, so ticket-based prioritization undercounts every theme the bot handles. Chatbase conversations come in as a third signal class, with a per-theme self_serve_failure_rate. - **Composability.** Pass churn or traffic data from other MCP servers into generate_product_plan via kpi_context, and the methodology adjusts priorities. Architecture Quick start Requires Node 20+. Not published to npm, so install from source: .env lives in the repo root. The server loads it from there regardless of the working directory it's launched from. Credentials Configure at least one source; the analysis adapts to whichever you set up. Without HelpScout there are no support tickets, so themes get no severity score and no convergence boost; ProductLift and Chatbase still rank themes by frequency and votes. | Variable | Required | Description | |----------|----------|-------------| | HELPSCOUT_APP_ID | No | OAuth app ID from https://secure.helpscout.net/apps/custom/ (set both or neither) | | HELPSCOUT_APP_SECRET | No | OAuth app secret | | PRODUCTLIFT_PORTALS | No | Multi-portal: name\|url\|key,name2\|url2\|key2 | | PRODUCTLIFT_PORTAL_URL | No | Single portal URL | | PRODUCTLIFT_API_KEY | No | Single portal Bearer token | | PRODUCTLIFT_PORTAL_NAME | No | Portal display name (default: default) | | CHATBASE_API_KEY | No | Account-wide secret key from Chatbase โ Settings โ API keys | | CHATBASE_AGENTS | No | Multi-agent: name\|agentId,name2\|agentId2 | | CHATBASE_AGENT_ID | No | Single agent id | | CHATBASE_AGENT_NAME | No | Single agent display name (default: default) | Chatbase API access needs a Standard plan or higher; on a lower plan the deflection signal becomes a warning. One agent per product gives product-level attribution a shared mailbox doesn't. Claude Desktop Add to ~/Library/Application Support/Claude/claude_desktop_config.json: Claude Code Or open Claude Code in the repo: it prompts you to approve the project .mcp.json. Verify Restart the client and ask it to run list_sources. It should list the sources you configured: HelpScout mailboxes, ProductLift portals and Chatbase agents. Tools Common filters Shared by synthesize_feedback and generate_product_plan. | Parameter | Type | Default | Description | |-----------|------|---------|-------------| | timeframe_days | number | 30 | Days to look back (1-90) | | top_voted_limit | number | 50 | Top-voted requests per portal (1-200). Recent requests in the timeframe are always included on top | | mailbox_id | string | โ | HelpScout mailbox ID | | mailbox_name | string | โ | HelpScout mailbox name (case-insensitive), resolved to an ID | | portal_name | string | โ | ProductLift portal | | agent_name | string | โ | Chatbase agent | | source_filter | string | โ | Chatbase conversation source, comma-separated for multiple (e.g. Widget or Iframe or WhatsApp,API). Case-insensitive | | include_comments | boolean | false | Also fetch customer comment text on feature requests (scrubbed; names and admin replies dropped) for theme matching and quotes. A modest gain for one extra call per request with comments; can take close to a minute on large portals |