Growth Strategist MCP Connector for Claude
A+AI agents asked for strategy always recommend the same five things: social media, engaging content, brand awareness. None of it is strategy — it's autocomplete. Growth Strategist demands specifics: name the person, prove channel fit, take a unique position, cite evidence, tie the outcome to revenue.
AI agents generating marketing strategy produce the same 5 things every time: "leverage social media", "create engaging content", "build brand awareness", "use SEO and paid ads", "partner with influencers". This is audience-blind, channel-mismatched, undifferentiated, unvalidated, vanity-driven noise. It's not strategy — it's autocomplete.
The Problem It Solves
AI-generated marketing fails on five axes:
- Audience blindness — "target social media users" without naming who
- Channel mismatch — recommending TikTok for B2B enterprise
- Generic advice — "leverage content marketing" with no unique position
- No evidence — claims without data, case studies, or precedents
- Vanity metrics — optimizing impressions instead of revenue
These aren't knowledge gaps. They're reasoning gaps. The agent never asks: who exactly is this for? Does this channel actually reach them? What can I say that no competitor can?
How It Works
Growth Strategist uses 5 Decision Pivots — boolean checkpoints that force the agent to reason through a strategic validation process before outputting any recommendation:
- icpNamed — Can you name the EXACT person? Job title, pain point, where they spend time.
- channelFitValidated — Evidence (not assumption) that this channel reaches the ICP.
- differentiationCommitted — A unique position that NO competitor can truthfully claim.
- evidenceCited — A data point, case study, or precedent supporting this tactic.
- outcomeMeasurable — Expected result tied to a business metric, not a vanity metric.
The tool validates logical consistency. If the agent says STRATEGY_PROVEN but icpNamed: false, the tool rejects with a clear explanation. If the differentiator is a feature list instead of a position, it rejects. If the expected outcome mentions "brand awareness" or "impressions", it rejects.
Why It Works
- Tool calls are obligations, instructions are suggestions. The agent can ignore "think about the audience" in a prompt. It cannot ignore a schema that requires naming the audience, explaining channel fit, and committing to a verdict.
- The commit pattern. The agent proposes its own verdict, then the server validates it against the pivots. This forced commitment deepens the reasoning — the agent must actively decide if its strategy is sound.
- Semantic traps. The engine catches domain-specific anti-patterns: generic ICP terms ("everyone", "businesses"), feature-list differentiators ("we offer", "best in class"), and vanity metric language ("impressions", "followers", "brand awareness").
Related Connectors
Ovulation and Fertile Window Calculator MCP
Predict ovulation dates, fertile windows, and peak conception days based on your menstrual cycle.
CMO Marketing Prover MCP
A CMO asked an AI for positioning. It said 'better and faster.' It proposes 'scale the ads' without a payback model. It trusts platform attribution 100%. It designs frictionless funnels that generate garbage leads. That is not marketing — that is a tactical wishlist. This tool forces five CMO-level marketing axes: category positioning, CAC payback physics, dark social attribution, intentional funnel friction, and budget allocation.
Opportunity Cost Prover MCP
AI agents operate in a vacuum. This engine cures 'tunnel vision' by forcing the LLM into a 6-pivot trap to map direct costs, quantify lost opportunities from discarded alternatives, identify irreversible tradeoffs, and prove the math.
M&A Synergy Calculator MCP
Financial modeling tool to estimate NPV and break-even period for M&A deals by calculating revenue, cost, and integration synergies.