PM33 MCP Server

claude /install-plugin https://github.com/b33-steve/pm33-mcp

Set your PM33 API key as an environment variable:

Remove theheadersblock from.mcp.json— Claude will use OAuth 2.0 PKCE automatically. You'll be prompted to log in to PM33 on first use.

Type any of these in Claude Code to run a PM workflow instantly:

You can also ask questions in natural language — the PM agent chains tools automatically:

5 data resources + 4 interactive MCP App views (HTML visualizations rendered inline in Claude Desktop):

- pm33://strategy/{workspaceId}— Strategic context
- pm33://backlog/{workspaceId}— Backlog summary
- pm33://velocity/{workspaceId}— Velocity metrics
- pm33://competitive/{tenantId}— Competitive landscape
- pm33://workspaces— Available workspaces
- pm33://ui/optimize-priorities— Priority scoring visualization
- pm33://ui/forecast-delivery— Delivery forecast chart
- pm33://ui/schedule-portfolio— Portfolio Gantt view
- pm33://ui/generate-prd— PRD document view

pm33-mcp/ .claude-plugin/ plugin.json # Plugin manifest commands/ prioritize.md # /pm33:prioritize — WSJF scoring forecast.md # /pm33:forecast — delivery forecasting prd.md # /pm33:prd — PRD generation competitors.md # /pm33:competitors — competitive intel respond.md # /pm33:respond — competitive response whatif.md # /pm33:whatif — scenario modeling schedule.md # /pm33:schedule — portfolio scheduling sprint.md # /pm33:sprint — full sprint planning skills/ pm33-product-manager/ SKILL.md # Multi-tool chaining workflows agents/ pm33-pm.md # Product manager agent persona .mcp.json # MCP server configuration settings.json # Activates pm33-pm agent by default

Perform queries and entity operations in your Fibery workspace.

Keep teams & agents coordinated automatically

Connect to the Taskade platform via MCP. Access tasks, projects, workflows, and AI agents in real-time through a unified workspace and API.

A universal remote MCP server that connects to popular productivity tools such as Notion, Monday, AirTable, and many more.

advanced-math-mcp — MCP server for linear algebra, calculus, and symbolic math. 17 tools with a unified evaluate() expression engine. Supports matrices, eigenvalues, SVD, integrals, limits, derivatives, and more.

Interact with Asana tasks, projects, workspaces, and comments using the Asana API.

Interact with the Asana API to manage tasks, projects, and workspaces.

An MCP interface for Atlassian products, including Jira and Bitbucket.

The Outcome Backcasting MCP is a strategic planning tool that helps you work backwards from a desired future outcome to identify the specific steps, resources, and dependencies needed to achieve your goals. Unlike traditional forward planning, backcasting starts with your end goal and creates a reverse roadmap to get there.