PMOS
An MCP server that gives an agent product data, feedback, metrics, sandbox analysis, and gated Jira tickets — so it can investigate drops, write PRDs, and file work with evidence.
README
PMOS
Product Manager Operating System. An MCP server that gives an agent product data, feedback, metrics, sandbox analysis, and gated Jira tickets — so it can investigate drops, write PRDs, and file work with evidence.
Implemented on OpenCode.
What you get
Tools
| Tool | Purpose |
|---|---|
get_product |
Product, users, competitors (default: ShipIt) |
list_features / get_feature |
Roadmap features + feedback count |
search_feedback / get_feedback_summary |
Quotes, sentiment, themes |
get_funnel_metrics |
Onboarding conversion over time |
get_feature_metrics |
Feature series (e.g. completion, step-3 drop-off) |
run_sandbox_analysis |
Isolated pandas/Python (Docker; off in compose) |
create_jira_ticket |
Preview first; approved=True only after the user says yes |
Resources: product://shipit · feature://{id} · metrics://onboarding
Prompts: generate_prd · analyze_feature · analyze_customer_feedback
Skills (.opencode/skills/): analyze feedback, feature analysis, write PRD, prioritize roadmap, create Jira tickets.
Demo data
Seeded product ShipIt — engineering PM SaaS vs Linear / Jira / Asana. Onboarding wizard is the leak: completion falling, Step 3 drop-off rising, mostly negative setup feedback.
Run
cp deployment/.env.example deployment/.env # set PMOS_MCP_TOKEN
cd deployment && docker compose up --build
Health: GET http://localhost:8000/health · MCP: http://localhost:8000/mcp
Client:
{
"mcpServers": {
"pmos": {
"url": "http://localhost:8000/mcp",
"headers": { "Authorization": "Bearer <PMOS_MCP_TOKEN>" }
}
}
}
Optional Jira: JIRA_URL, JIRA_EMAIL, JIRA_API_TOKEN, JIRA_PROJECT in deployment/.env. Missing creds → local stub. Need a real Jira Software project (not Atlas).
cd mcp && python tests/run_tests.py
SQLite locally if PMOS_DATABASE_URL is unset; Postgres in Docker.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.