spm-mcp

Cursor for product management. Expert document review as MCP tools.

AI made engineering 10x faster. But deciding what to build didn't get faster. SPM fixes the input with 30 domain-specific expert reviews that score your product documents against the standards senior PMs actually use.

npx spm-mcp

The problem

AI agents build what you specify, including every blind spot. A vague spec used to waste a sprint. Now it ships to production in hours. SPM catches the blind spots before they become shipped code.

What SPM reviews

Not just PRDs. Every document in the PM lifecycle:

• Strategy: Product Roadmap, Growth Strategy, Go-to-Market, OKR Planning, Product Vision
• Analysis: Competitive Analysis, Market Research, Product Metrics, Stakeholder Management
• Execution: User Stories, Feature Spec, Sprint Planning, PRD to Jira, Release Notes, Test Cases
• Discovery: Problem Statement, Persona, Jobs-to-be-Done, Opportunity Assessment

30 built-in expert reviews. Or bring your own template with spm_create_custom_nano_app -- paste your favorite PRD or describe your sections, and SPM creates a personalized review in seconds.

Quick start

Option A: Guided setup (recommended)

npx spm-mcp

First run auto-detects no API key and walks you through setup:

1. Opens your browser to sign in
2. You generate an API key on your Profile page
3. Paste it back in the terminal
4. Key saved to ~/.spm/config.json. Done.

Option B: Manual setup

# 1. Get your key at https://superproductmanager.ai?utm_source=npm&utm_medium=readme&utm_campaign=mcp > Profile > Generate API Key
# 2. Set it
export SPM_API_KEY=spm_k_your_key_here
# 3. Run
npx spm-mcp

Option C: claude.ai connector (recommended for non-terminal users)

Connect SPM directly inside claude.ai with an interactive onboarding dashboard:

1. Go to spm-mcp.superproductmanager.ai to get your personalized connector URL
2. In claude.ai, go to Settings > Connectors > Add custom connector
3. Paste your URL and click Add
4. Switch to Cowork mode, type "get started"

SPM renders an interactive welcome dashboard right in the chat. Pick a built-in review template or paste your own PRD to create a custom one.

Watch the 2-minute setup video: youtube.com/watch?v=1s8EpRJCJ68

Tools

| Tool | What it does | |------|-------------| | spm_create_custom_nano_app | Start here. Paste your favorite PRD, describe your template sections, or pass evaluation criteria. Creates a personalized review that uses your terminology and covers your sections. | | spm_list_nano_apps | Browse 30 built-in expert reviews if you don't have your own template. | | spm_analyze | Score a document against expert expectations. Every gap scored 0-1.0 with evidence. | | spm_clarify | Decision-forcing questions for the weakest gaps. Questions escalate when you give vague answers. | | spm_evaluate | Re-score gaps after clarification rounds. Tracks progress. Use after every 3 rounds of spm_clarify. | | spm_improve | Generate paste-ready improvements grounded in your answers, not AI hallucination. |

How it works

Your document
    > spm_analyze     Scores every gap 0-1.0 against expert expectations
    > spm_clarify     Asks the questions your stakeholder would ask
    > spm_evaluate    Re-scores. Did the gap close?
    > spm_improve     Generates improvements from YOUR answers

The clarification questions are the product. They surface the assumptions you've been carrying without examining. When you dodge, they escalate: evidence first, then action directives, then assumptions made on your behalf. Like a principal PM review, not a chatbot.

Example: Bring your own template

You:    Here's my team's PRD template [pastes PRD]
SPM:    Detected 9 sections. Created "PRD Review" with 5 expectations:

        Expectation                  | Rules                          | Checks
        Problem & Goal               | Problem, Goal                  | Data-backed problem, measurable goal
        Users & Solution             | Target Users, Proposed Solution| Specific personas, buildable solution
        Metrics & Timeline           | Success Metrics, Timeline      | Baselines, phased delivery
        Technical & Risks            | Technical Approach, Risks      | Dependencies, mitigations
        Out of Scope                 | Out of Scope                   | Explicit boundary list

You:    Looks good. Analyze this PRD.
SPM:    [scores against YOUR expectations, not generic ones]

Example: Built-in review

You:    Analyze this PRD with prd_critique
SPM:    4 expectations scored. Problem Definition: 43/100. Success Metrics: 15/100.

You:    Clarify the weakest gap
SPM:    "Is operator churn or player registration drop-off your primary counter-metric?"

You:    Operator churn. If >20% revert to WhatsApp, we've failed.
SPM:    [re-evaluates] Counter-metric: 0 > 0.9. Now targeting: Instrumentation plan.

You:    Improve the success metrics section
SPM:    [generates paste-ready content grounded in your "operator churn" decision]

Average documents improve from 35% to 82% in three rounds.

Setup for AI coding assistants

Claude Code

claude mcp add spm -- npx spm-mcp

Or add to .claude/settings.json. If you ran npx spm-mcp setup already, the key is in ~/.spm/config.json and no env var is needed:

{
  "mcpServers": {
    "spm": {
      "command": "npx",
      "args": ["spm-mcp"]
    }
  }
}

Cursor

Add to MCP settings:

{
  "spm": {
    "command": "npx",
    "args": ["spm-mcp"],
    "env": {
      "SPM_API_KEY": "spm_k_your_key_here"
    }
  }
}

Windsurf

Add to MCP configuration with the same command and env structure.

Environment variables

| Variable | Required | Default | Description | |----------|----------|---------|-------------| | SPM_API_KEY | Only if no ~/.spm/config.json | n/a | Your API key. Run npx spm-mcp for guided setup. | | SPM_SUPABASE_URL | No | Production | Override for development | | SPM_SUPABASE_ANON_KEY | No | Production | Override for development | | SPM_CLOUD_FUNCTIONS_BASE | No | Production | Override Cloud Functions URL |

API key resolution order: SPM_API_KEY env var > ~/.spm/config.json > setup prompt.

Security

• No filesystem access. SPM never reads your local files, SSH keys, or credentials.
• No postinstall scripts. Nothing runs on npm install.
• Minimal env access. Reads 4 optional env vars and ~/.spm/config.json. No broad process.env access.
• Network calls only when tools are invoked. Not on import, not on install.
• Source included. TypeScript source ships alongside compiled JS for auditability.
• Zero known vulnerabilities. npm audit clean.

Also available as

• Chrome extension. Reviews documents inside Google Docs, Notion, ClickUp, Linear. Install from Chrome Web Store
• Web app. Paste any document, full analysis in 30 seconds. superproductmanager.ai

Links

• Website
• claude.ai Connector Setup
• Setup Video Tutorial
• Chrome Extension

License

MIT