PMFlow MCP
# PMFlow MCP (Lite)
[](LICENSE)
[](https://python.org)
[](https://modelcontextprotocol.io)
**Autonomous Product Management Workflow, PRD Engine & BDD Story Validator for AI Agents**
PMFlow MCP gives AI agents (Claude Desktop, Cursor, Devin, Roo-Code) the capabilities of a Senior Technical Product Manager. It generates structured Product Requirement Documents (PRDs), decomposes epics into testable User Stories, validates Given/When/Then acceptance criteria for testability, and exports markdown backlogs.
---
## 🚀 Features (Lite Edition)
- **Automated PRD Generator (`generate_prd`):** Creates complete PRD specifications with MoSCoW prioritization, functional requirements, technical constraints, risks, and measurable KPIs.
- **Atomic Story Decomposer (`decompose_stories`):** Formats requirements into standard agile format: *"As a [persona], I want [goal], so that [benefit]"* with estimated story points.
- **BDD/Gherkin Syntax Validator (`validate_acceptance_criteria`):** Enforces Given/When/Then syntax, flags ambiguous terms (e.g., "fast", "intuitive", "easy") that cause agent drift, and calculates a 0-100 testability score.
- **Markdown Specification Exporter (`export_markdown_specs`):** Generates clean, commit-ready documentation for repositories.
---
## 📦 Installation & Setup
```bash
git clone https://github.com/johannschiffer/pmflow-mcp.git
cd pmflow-mcp
pip install -e .
```
### Configuration with Claude Desktop / Cursor
Add to your `claude_desktop_config.json`:
```json
{
"mcpServers": {
"pmflow": {
"command": "python3",
"args": ["-m", "pmflow.server"]
}
}
}
```
---
## âš¡ Quick CLI Usage
```bash
# Generate a PRD in Markdown
pmflow prd \
--title "Payment Gateway Integration" \
--problem "Customers cannot check out with Apple Pay" \
--audience "Mobile checkout shoppers" \
--features "Stripe SDK setup" "Apple Pay button" "Webhook listener" \
--markdown
# Validate BDD Acceptance Criteria
pmflow validate --criteria \
"Given user is on checkout page" \
"When user taps Apple Pay button" \
"Then payment sheet opens within 300ms"
```
---
## 💼 Upgrade to PMFlow Pro
Need enterprise capabilities for multi-agent swarms? Check out **PMFlow Pro**:
- **User Story Dependency DAG Engine:** Cycle detection via Kahn's algorithm and critical path calculation in SQLite WAL.
- **Sprint Velocity & Capacity Forecaster:** Monte Carlo simulation of agent capacity and bottleneck alerts.
- **Issue Tracker Exporter:** Automatic sync with Jira, Linear, and GitHub Issues.
- **Docker Compose:** Production containerization ready for agent clusters.
Available at [Gumroad](https://johanld.gumroad.com/).
---
## 📄 License
MIT © Johann Schiffer
TDQS
Scored across 4 tools
Each tool targets a distinct artifact and action in the pipeline: PRD generation, story decomposition, criteria validation, and markdown export. There is no meaningful overlap, so an agent can select the right tool unambiguously.
All four tools follow a consistent snake_case verb_noun pattern (generate_prd, decompose_stories, validate_acceptance_criteria, export_markdown_specs). The convention is uniform and predictable.
Four tools map cleanly onto the generate-decompose-validate-export pipeline, which is well-scoped rather than bloated. It is slightly thin, but each tool clearly earns its place.
The core generation pipeline is covered, but there are no read/update/delete operations, so an agent cannot retrieve, revise, or list existing PRDs and stories. This is a notable gap for a document-authoring workflow.