The math layer for marketing agents: 81 skills, 66 with deterministic engines th
The math layer for marketing agents: 81 skills, 66 with deterministic engines that return numbers and a verdict. Keep your writing skills, add the arithmetic. MIT, no API key.
active Production-safe Score 95/100 http no auth
At a glance
| Endpoint | https://aaj-engines-mcp.sarojkjha10.workers.dev/mcp |
|---|---|
| Source | https://github.com/sarojkjha/aaj-marketing-skills |
| Transport | http |
| Tools | 5 |
| Auth | none |
| First seen | 2026-11-02 20:27:27 |
| Last checked | 2026-11-17 22:01:33 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 287 / 500 ms |
| Last successful check | 2026-11-17 22:01:33 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (5)
list_engines— Lists every AAJ marketing engine: its id, the question it answers, and its category. Engines cover unit economics, pipeline forecast, budgetdescribe_engine— Shows one engine's input schema: required fields, units, alternative shapes, and a worked example. Engines reject bad input rather than guesrun_engine— 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 worksearch_skills— Finds AAJ marketing skills by the problem they solve — 'churn is rising', 'we're launching next month', 'not showing up in AI answers'. Retuget_skill— 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.
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 22:01:33 | ✓ | ✓ | 203 ms | 94 | active |
| 2026-11-17 21:46:26 | ✓ | ✓ | 230 ms | 94 | active |
| 2026-11-17 21:31:20 | ✓ | ✓ | 472 ms | 91 | active |
| 2026-11-17 21:16:08 | ✓ | ✓ | 456 ms | 91 | active |
| 2026-11-17 21:01:01 | ✓ | ✓ | 443 ms | 91 | active |
| 2026-11-17 20:45:50 | ✓ | ✓ | 239 ms | 94 | active |
| 2026-11-17 20:30:48 | ✓ | ✓ | 263 ms | 94 | active |
| 2026-11-17 20:15:43 | ✓ | ✓ | 421 ms | 91 | active |
| 2026-11-17 19:59:39 | ✓ | ✓ | 268 ms | 94 | active |
| 2026-11-17 19:44:32 | ✓ | ✓ | 396 ms | 91 | active |
| 2026-11-17 19:29:27 | ✓ | ✓ | 231 ms | 94 | active |
| 2026-11-17 19:14:26 | ✓ | ✓ | 246 ms | 94 | active |
| 2026-11-17 18:58:40 | ✓ | ✓ | 253 ms | 94 | active |
| 2026-11-17 18:43:38 | ✓ | ✓ | 289 ms | 94 | active |
| 2026-11-17 18:28:37 | ✓ | ✓ | 358 ms | 91 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://aaj-engines-mcp.sarojkjha10.workers.dev/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/aaj-engines-mcp-sarojkjha10-workers-dev-mcp # JSON