pm33_query_backlogLABSCO SUMMARY
Prioritisation, forecasting and PRDs that read from your actual backlog.
The nine tools chain naturally: query the backlog, score it against strategy, then forecast what that ordering means for a ship date. Every answer depends on what PM33 already knows about your product, so the quality tracks how complete your workspace is.
What it is
The MCP server for PM33, an AI product-management platform: nine tools over your backlog, velocity, strategy and competitive data, plus nine resources, four of which are interactive views.
What you get
- The backlog queried, scored with WSJF, and checked against strategy (pm33_query_backlog, pm33_optimize_priorities, pm33_score_alignment)
- A delivery forecast with confidence intervals, built from measured velocity (pm33_analyze_velocity, pm33_forecast_delivery)
- What-if scenarios on scope, timeline or resources, with delivery, cost and risk impact modelled (pm33_analyze_scenario)
- Epics scheduled across team lanes, respecting velocity and dependencies (pm33_schedule_portfolio)
- A PRD generated with strategic context and the competitive landscape (pm33_generate_prd)
- Competitive intelligence alerts with recommended actions (pm33_competitive_threats)
Requirements
A PM33 account. Sign in over OAuth when the client first connects, or send an API key from Settings > Integrations > MCP Server in the x-api-key header.
Setup effort
Add the hosted endpoint, then sign in — paste it into your client, then approve the OAuth sign-in
USE CASES
01
Deciding what to build next
Pull the backlog, score it with WSJF, and check the top items against the strategy.
02
Answering when will this ship
Read the team's velocity, then forecast the epic with confidence intervals rather than a single date.
03
Modelling a change before you commit to it
Run the scenario for the scope or timeline shift and read the delivery, cost and risk impact.
04
Writing a PRD without starting from a blank page
Generate it with the backlog context and competitive landscape already folded in.
05
Deciding how to respond to a competitor
Read the threat, then model what responding would cost the roadmap.
06
Laying out a quarter across several teams
Schedule the epics into team lanes with velocity and dependencies respected.
9 tools
Listed in project docs. Your client may show a different list.
pm33_optimize_prioritiespm33_score_alignmentpm33_forecast_deliverypm33_analyze_velocitypm33_competitive_threatspm33_generate_prdpm33_analyze_scenariopm33_schedule_portfolioBEFORE YOU INSTALL
What to know first
Tools you get
9 tools named in the project's documentation.
Requires
A PM33 account
Where it runs
All 3 documented setups connect to a hosted endpoint.
INSTALLATION
Connect your client
Server setup
ENDPOINT URL
https://app.deepwind.ai/mcpAdd this hosted endpoint to your MCP client using the credentials listed under Requirements.
MCP Clients
Claude Code
CLAUDE CODE · TERMINAL
claude mcp add pm33 --transport http https://app.deepwind.ai/mcpClaude Code opens a browser to sign in to PM33 over OAuth the first time the server is used.
Any MCP client — OAuth
ANY MCP CLIENT — OAUTH · JSON
{
"mcpServers": {
"pm33": {
"url": "https://app.deepwind.ai/mcp",
"type": "http"
}
}
}Clients that support OAuth open a browser for PM33 consent and cache the token — no API key needed.
Any MCP client — API Key
ANY MCP CLIENT — API KEY · JSON
{
"mcpServers": {
"pm33": {
"url": "https://app.deepwind.ai/mcp",
"type": "http",
"headers": {
"x-api-key": "<YOUR_API_KEY>"
}
}
}
}<YOUR_API_KEY> is an API key from Settings > Integrations > MCP Server in PM33. The key needs at least the mcp:enabled scope.
