Deterministic marketing math for AI agents: LTV:CAC, pipeline coverage, A/B tests, pricing.
Scored across 5 tools
Each tool has a clearly distinct role: list/search for discovery, get/describe for detail, and run for execution. Engine-related and skill-related tools are cleanly separated by resource, so an agent can choose without overlapping-purpose confusion.
All five names follow a consistent snake_case verb_noun pattern: describe_engine, get_skill, list_engines, run_engine, search_skills. There are no mixed conventions or vague standalone verbs.
Five tools is well-scoped for a small catalog of engines and skills. Each tool earns its place by covering a distinct discovery, inspection, or execution need.
The surface supports discovering, inspecting, and running engines, plus finding and reading skills. A browse/list-all-skills operation is missing, but search_skills and get_skill cover most practical workflows.
Shows one engine's input schema: required fields, units, alternative shapes, and a worked example. Engines reject bad input rather than guessing.
| Name | Required | Description | Default |
|---|---|---|---|
| engine | Yes | Engine id. |
Returns the full method for one skill: when to use it, the steps, the quality bar, and how to run its engine if it has one.
| Name | Required | Description | Default |
|---|---|---|---|
| skill | Yes | Skill slug. |
Lists every AAJ marketing engine: its id, the question it answers, and its category. Engines cover unit economics, pipeline forecast, budget allocation, retention, A/B significance, SEO/GEO scoring, ad spend and pricing.
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Optional filter. Words are matched against the engine's category, id and skill title (for example "pricing", "retention" or "seo audit"), then against its summary. |
Runs an AAJ engine and returns its verdict. Give input as an object of the engine's fields. Omit input to run the engine's built-in worked example. Engines are deterministic, offline, and validate their input — a wrong unit is reported as an error, not absorbed into a confident answer.
| Name | Required | Description | Default |
|---|---|---|---|
| input | No | The engine's configuration object. Some engines also accept a named mode as a plain string (for example 'design' or 'readout'). Omit for the demo. | |
| engine | Yes | Engine id. |
Finds AAJ marketing skills by the problem they solve — 'churn is rising', 'we're launching next month', 'not showing up in AI answers'. Returns matching methods and marks which have a runnable engine.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results, default 8. | |
| query | Yes | The problem, in plain words. |
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
search_skills1 field changedInput schema / properties / limit / maximumPrevious value: -73New value: +81describe_engine1 field changedInput schema / properties / engine / descriptionPrevious value: -"Engine id from list_engines."New value: +"Engine id."get_skill1 field changedInput schema / properties / skill / descriptionPrevious value: -"Skill slug from search_skills."New value: +"Skill slug."run_engine2 fields changedInput schema / properties / engine / descriptionPrevious value: -"Engine id from list_engines."New value: +"Engine id."Input schema / properties / input / descriptionPrevious value: -"The engine's configuration object. Some engines also accept a named mode as a plain string (for example 'design' or 'readout') — describe_engine says which. Omit for the demo."New value: +"The engine's configuration object. Some engines also accept a named mode as a plain string (for example 'design' or 'readout'). Omit for the demo."list_engines1 field changedInput schema / properties / category / descriptionPrevious value: -"Optional filter, matched loosely against the engine's category."New value: +"Optional filter. Words are matched against the engine's category, id and skill title (for example \"pricing\", \"retention\" or \"seo audit\"), then against its summary."describe_engineget_skilllist_enginesrun_enginesearch_skillsDeterministic what-if & scenario simulation for AI agents: projections, sensitivity & break-even.
AI marketing agent for Google Ads, Meta, GA4, TikTok, LinkedIn, Shopify, HubSpot and more.
The hidden intelligence for AI marketing agents. Real campaign data, not LLM guesses.
How to market a product to AI agents: readiness, placement, measurement, 7-day trial.
Add one secure layer between your agents and this server.
