Enables reading emails for morning briefing generation.
Provides read-only access to Jira analytics for metrics agent and allows creating Jira tickets through the prd_ticket agent.
Supports writing morning briefings and end-of-day dumps into daily notes, and creating PRDs via the prd_ticket agent.
Powers grounded Q&A and note upkeep over a local Obsidian vault using a RAG index.
Enables read-only access to PostHog analytics for metrics and briefing agents.
Integrates with Slack for sending morning briefings and end-of-day dumps.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@pm-agents give me my morning briefing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A multi-agent product-management copilot that automates a PM's operating rhythm: morning briefings, metrics answers, grounded knowledge lookups over an Obsidian vault, and PRD/ticket drafting — each a specialised backend agent with real integrations and hard guardrails.
Built and used daily by a working product manager. Runs locally on Windows against a Claude subscription (no per-token API billing) by driving the logged-in claude CLI in print mode, with tools exposed as a local stdio MCP server.
A single-agent orchestrator (all tools) plus four specialists:
Specialist | Does | External creds |
| Vault Q&A grounded in a local RAG index; guarded note upkeep | none (local only) |
| PostHog + Jira analytics, anomaly/OKR watch (read-only) | PostHog, Jira |
| Morning briefing + EOD dump written into the daily notes | Jira, Slack, Notion, PostHog, Gmail |
| Draft + create PRDs (Notion) and Jira tickets, on confirmation | Notion, Jira |
Related MCP server: PM-Kit
Print-mode + MCP, not the streaming SDK. The Agent SDK's streaming stdio transport does not complete its control handshake with the native claude.exe on Windows (verified: hangs on initialize). claude -p works reliably, so the runner drives that directly and exposes the Python tools via --mcp-config pointing at pm_agents.mcp_server. Pragmatism over purity.
Allowlist-only tool execution. Tools are pre-approved through an explicit --allowedTools allowlist plus --strict-mcp-config — no blanket permission bypass. Each specialist gets the minimum tool set for its job.
Guardrails in code, not prompts (pm_agents/guardrails.py): production-database references are hard-blocked by regex before any tool executes; write operations require explicit confirmation. The model is never trusted to self-police.
Grounded-only answers. The knowledge agent must quote retrieved chunks; if retrieval returns nothing it says so instead of improvising.
One agent, one prompt file. Each agent's behaviour lives in a single markdown file under pm_agents/prompts/ — reviewable, diffable, no prompt spaghetti.
Scheduling: Windows Task Scheduler entries (scripts/schedule_tasks.ps1) drive the morning/EOD/weekly runs.
python -m venv .venv && .venv/Scripts/activate
pip install -r requirements.txt
cp .env.example .env # fill in your own tokens — nothing is committed
python scripts/smoke_test.pypm_agents/
agents/ # the four specialists
integrations/ # jira, notion, slack, gmail, posthog clients (thin, typed)
prompts/ # one behaviour file per agent
tools/ # vault + RAG tools
guardrails.py # hard safety checks (prod-DB block, allowlists)
mcp_server.py # stdio MCP server exposing the tools
scripts/ # entrypoints: morning brief, EOD, weekly, chat, diagnosticsThis server cannot be deployed
AI-native project management for tasks, docs, collaboration, and agents.
AI-native project management + agent memory: tasks, sprints, risk, burnout, knowledge search.
Product intelligence for AI agents — query a Revelica workspace's ideas, specs, and research.
AI-powered product management: backlog optimization, scheduling, forecasting, and PRD generation.
