Pabs
Connects your AI coding tools to PABS, a product strategy platform that generates PRDs, competitor analysis, and design hypotheses from a brief. Your AI can call get_full_context to load the entire strategy at session start, then use ask_pabs_agent to check feature alignment or report_learning to push observations back into the strategy loop. Each learning gets evaluated by PABS and queued for founder review before the strategy updates. Useful when you want your AI builder to know the target audience and design constraints before writing code, and to surface drift between what was planned and what got built. Authentication is one bearer token per plan, generated from the PABS Connect tab.
- tools
- 18
- transport
- HTTP
- last updated
- May 29, 2026
Tools
18 toolsPublic tool metadata for what this MCP can expose to an agent.
get_full_contextEverything in one call: brief, strategy, competitor analysis, documents, decisions, hypotheses, action plan, latest pulse, recent learnings.
Everything in one call: brief, strategy, competitor analysis, documents, decisions, hypotheses, action plan, latest pulse, recent learnings.
No parameter schema in public metadata yet.
get_briefProblem statement, target audience, goals, constraints, timeline
Problem statement, target audience, goals, constraints, timeline
No parameter schema in public metadata yet.
get_product_strategyDesign hypotheses, customer goals, pain points, design vision, success metrics, experience principles
Design hypotheses, customer goals, pain points, design vision, success metrics, experience principles
No parameter schema in public metadata yet.
get_competitor_analysisMarket intelligence, competitive positioning, opportunity analysis
Market intelligence, competitive positioning, opportunity analysis
No parameter schema in public metadata yet.
get_prdProduct Requirements Document generated for AI code builders
Product Requirements Document generated for AI code builders
No parameter schema in public metadata yet.
get_documentsAll generated documents: PRD, Statement of Work, Venture Brief
All generated documents: PRD, Statement of Work, Venture Brief
No parameter schema in public metadata yet.
get_decisionsKey assumptions, information gaps with priority/impact, recommended next steps
Key assumptions, information gaps with priority/impact, recommended next steps
No parameter schema in public metadata yet.
get_hypothesesDesign hypotheses with target audience and success indicators
Design hypotheses with target audience and success indicators
No parameter schema in public metadata yet.
get_action_planStaged activities with tools, durations, and deliverables
Staged activities with tools, durations, and deliverables
No parameter schema in public metadata yet.
get_pulseCurrent strategic Pulse: verdict, recommended next move, activation level
Current strategic Pulse: verdict, recommended next move, activation level
No parameter schema in public metadata yet.
get_learningsAll captured learnings — evaluated and decided — with the full decision history
All captured learnings — evaluated and decided — with the full decision history
No parameter schema in public metadata yet.
get_pending_learningsLearnings PABS has evaluated but that need a human decision
Learnings PABS has evaluated but that need a human decision
No parameter schema in public metadata yet.
get_pulse_scheduleCurrent Pulse cadence: day, time, timezone, frequency, next run
Current Pulse cadence: day, time, timezone, frequency, next run
No parameter schema in public metadata yet.
ask_pabs_agentAsk a strategic question. Returns alignment score, recommendations, and considerations. Automatically captures observations or implementation drift.
Ask a strategic question. Returns alignment score, recommendations, and considerations. Automatically captures observations or implementation drift.
No parameter schema in public metadata yet.
report_learningPush a real-world observation into the strategy feedback loop. PABS evaluates its impact and queues it for the founder to review.
Push a real-world observation into the strategy feedback loop. PABS evaluates its impact and queues it for the founder to review.
No parameter schema in public metadata yet.
decide_learningApprove, reject, or modify a pending learning inline — without opening PABS.
Approve, reject, or modify a pending learning inline — without opening PABS.
No parameter schema in public metadata yet.
trigger_pulseQueue a fresh strategic Pulse after a significant build session or analytics review.
Queue a fresh strategic Pulse after a significant build session or analytics review.
No parameter schema in public metadata yet.
schedule_pulseSet the agentic Pulse cadence (frequency, day, hour, timezone).
Set the agentic Pulse cadence (frequency, day, hour, timezone).
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
PABS MCP Server
Give your AI coding tools live access to your product strategy.
PABS is a product strategy platform that turns a brief into a full strategy — hypotheses, competitor analysis, PRD, and a living pulse of your venture's health. The MCP server exposes that strategy to any MCP-compatible AI tool so it can build with context, not guesses.
When your AI builder knows the target audience, design hypotheses, and current strategic verdict, it makes better decisions. When it spots a gap between what was planned and what was built, it can report it back — and PABS queues it for your review.
Connection
Transport: Streamable HTTP (MCP 2025 spec)
Server URL: https://pabs.co.nz/api/mcp/{your-token}
Authentication: Bearer token (one per plan, generated in the PABS app)
Get your token
- Open your plan in PABS
- Go to the Connect tab (or click the plug icon)
- Click Generate Token
- Copy the server URL — it includes your token
Connect to your AI tool
Claude Desktop
Add to claude_desktop_config.json:
Details
- Repository
- github.com/pdunovits/pabs-mcp
- Website
- pabs.co.nz
- Transport
- HTTP
- Registry
- MCP registry, active