Adds two new MCP-backed plugins for analytics practitioners: - adobe-analytics — 5 skills targeting the Adobe Analytics MCP server (KPI pulse, top movers, conversion funnel analysis, segment performance comparator, executive briefing). - adobe-cja — 6 skills targeting the Customer Journey Analytics MCP server (KPI pulse, top movers, funnel health check, dimension analysis, segment performance comparator, executive briefing). Each plugin ships a .mcp.json pointing at its hosted MCP endpoint (https://aa-mcp.adobe.io/mcp and https://cja-mcp.adobe.io/mcp) so the skills work out of the box once the user has product access. Repo-wide updates: - Register both plugins in .claude-plugin/marketplace.json. - Add a new "Analytics" group to the top-level README under For Business, with per-skill descriptions, sample prompts, and links to each plugin README, plus install commands in the Installation section. - Add CODEOWNERS entries for the two new plugin directories. - Every new SKILL.md declares license: Apache-2.0 in its frontmatter. Co-authored-by: Cursor <cursoragent@cursor.com>
4.6 KiB
Adobe Customer Journey Analytics (CJA) MCP Plugin
Use the CJA MCP server as an analytics copilot: KPI monitoring, funnel and segment analysis, dimension profiling, and executive readouts — all driven from natural-language requests in Claude Code, Cursor, and other MCP clients.
Installation
Claude Code:
/plugin marketplace add adobe/skills
/plugin install adobe-cja@adobe-skills
Cursor / other MCP clients: Configure the MCP server entry per your environment (see below).
MCP server
{
"mcpServers": {
"adobe-cja": {
"type": "http",
"url": "https://cja-mcp.adobe.io/mcp"
}
}
}
Requests require IMS auth headers (Authorization, x-gw-ims-org-id, x-gw-ims-user-id, etc.); an OAuth proxy may inject these. Include x-data-view-id when required.
This repo's .mcp.json is a template only.
Skills
| Skill | Description | Try it |
|---|---|---|
| Monitor & investigate — Skills that track day-to-day KPI movement and dig into unexpected shifts. | ||
| cja-kpi-pulse | KPI digest with period-over-period change, trend direction, and dimension breakdown |
|
| cja-top-movers-watchlist | Ranks dimension items by biggest gain or loss for a metric |
|
| Analyze — Skills that go deeper into a specific question — funnels, dimensions, segment differences. | ||
| cja-funnel-health-check | Step-by-step fallout analysis across a multi-step conversion funnel |
|
| cja-dimension-analysis | Cardinality, distribution, trends, anomalies, and data quality for a dimension |
|
| cja-segment-performance-comparator | Side-by-side KPI comparison across two or more audience segments |
|
| Deliver — Skills that produce stakeholder-ready output, like narrative briefings for leadership and business reviews. | ||
| cja-executive-briefing | Narrative performance summary ready for leadership or QBR |
|
Usage
Each skill's SKILL.md contains the trigger description, phased workflow, MCP tool calls, and HTML output templates. Your MCP client routes natural-language requests to the matching skill automatically via the YAML description field.
Contributing
To add a new skill, create a skills/<skill-id>/SKILL.md following the existing pattern (YAML frontmatter with name/description, phased workflow, MCP tool calls, HTML template). Keep name: stable — it is used for routing.
See the repository CONTRIBUTING.md for the broader contribution process.