Skip to main content
Glama
adobe-cja-mcp
by markhilton

Adobe Customer Journey Analytics MCP Server

PyPI version Python 3.10+ License: MIT

Model Context Protocol (MCP) server for Adobe Customer Journey Analytics (CJA), enabling AI-powered analytics queries through Claude and other MCP clients.

⚡ Quick Start (Simplest Setup)

No repository cloning required! Users can run this MCP server with just 2 steps:

1. Install uv (Python package manager)

# macOS/Linux
brew install uv

# Or with curl
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

2. Configure Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "Adobe CJA": {
      "command": "uvx",
      "args": ["adobe-cja-mcp"],
      "env": {
        "ADOBE_CLIENT_ID": "your_client_id_here",
        "ADOBE_CLIENT_SECRET": "your_client_secret_here",
        "ADOBE_ORG_ID": "your_org_id@AdobeOrg",
        "ADOBE_DATA_VIEW_ID": "dv_your_dataview_id"
      }
    }
  }
}

That's it!

Restart Claude Desktop and uvx will automatically download and run the MCP server from PyPI - just like npx for Node.js!


Related MCP server: Criteo MCP Server

Overview

This MCP server provides tools for querying Adobe CJA data, including:

  • Running analytics reports with dimensions and metrics

  • Multi-dimensional breakdown analysis

  • Time-series trend analysis at various granularities

  • Searching and filtering dimension values

  • Listing available dimensions and metrics

  • Data view configuration access

Features

Core Reporting Tools (MVP):

  • Run ranked reports with dimensions and metrics

  • Get top N items for any dimension

  • List available dimensions and metrics

  • Access data view configuration

Advanced Reporting:

  • Breakdown Reports: Multi-dimensional analysis (e.g., pages by device type)

  • Trended Reports: Time-series analysis with hourly/daily/weekly/monthly granularity

  • Dimension Search: Find specific dimension values (pages, products, campaigns)

  • Segment Support: Filter reports with segment IDs

Adobe CJA API Permissions

Required Permissions Scope

For this MCP server to function, your Adobe API credentials (OAuth 2.0 Server-to-Server) must have the following permissions granted in Adobe Admin Console.

Authentication Scopes

Your API credentials require these OAuth scopes:

openid
AdobeID
read_organizations
additional_info.projectedProductContext
cja.reporting         # CRITICAL - Required for all reporting operations
cja.workspace         # Required for workspace objects (projects, filters, etc.)

Critical Permissions (Required for Core Functionality)

Without these permissions, the MCP server cannot perform analytics queries:

1. CJA Reporting API - Ranked Reports

  • API Endpoint: POST https://cja.adobe.io/reports

  • Permission: CJA Reporting API Access

  • Required For:

    • Running analytical reports with dimensions and metrics

    • Querying website performance data (sessions, page views, conversions)

    • Generating attribution analysis

    • Creating breakdown reports

  • MCP Tools Blocked Without Permission:

    • cja_run_report - Main reporting tool

    • cja_get_top_items - Top performers analysis

    • cja_get_trended_report - Time-series analysis

    • cja_get_breakdown_report - Multi-dimensional breakdowns

    • cja_get_sessions_data - Session analytics

    • cja_get_conversions_data - Conversion tracking

    • cja_get_attribution_analysis - Attribution modeling

    • cja_get_funnel_analysis - Funnel analysis

2. CJA Reporting API - Top Items

  • API Endpoint: GET https://cja.adobe.io/reports/topItems

  • Permission: CJA Reporting API Access

  • Required For:

    • Ranking dimension items by metrics

    • Finding top pages, products, campaigns

  • MCP Tools Blocked Without Permission:

    • cja_get_top_items (alternative implementation)

Working Permissions (Read-Only Access)

These permissions are typically granted by default for read-only CJA API access and should already be available:

  1. GET /data/dataviews/{id}/dimensions - List available dimensions

  2. GET /data/dataviews/{id}/metrics - List available metrics

  3. GET /data/dataviews/{id} - Get data view configuration details

  4. GET /calculatedmetrics - List calculated metrics

  5. GET /filters - List filters/segments

  6. GET /dateranges - List date ranges

  7. GET /annotations - List annotations

  8. GET /projects - List Analysis Workspace projects

  9. GET /data/connections - List data connections

Optional Permissions (Enhanced Features)

These permissions enable additional features but are not required for basic operation:

Individual Dimension/Metric Details

  • Endpoints:

    • GET /data/dataviews/{id}/dimensions/{dimId}

    • GET /data/dataviews/{id}/metrics/{metricId}

  • Benefit: Get detailed metadata for specific dimensions/metrics

  • Workaround: Use list endpoints instead

Filter Validation

  • Endpoint: POST /filters/validate

  • Benefit: Validate filter definitions before use

  • Workaround: Test filters directly in reports

List All Data Views

  • Endpoint: GET /dataviews

  • Benefit: Discover all available data views

  • Workaround: Use configured data view ID from environment variables

Setting Up Permissions in Adobe Admin Console

Step 1: Navigate to API Credentials

  1. Log in to Adobe Admin Console

  2. Navigate to Products → Customer Journey Analytics

  3. Click on API Credentials

  4. Select your OAuth Server-to-Server credential (Client ID)

Step 2: Add Product Profile

  1. Click Add Product Profile

  2. Select a profile that includes CJA Reporting API Access

  3. Ensure the profile has the following permissions:

    • Reporting API: Full access to POST /reports and GET /reports/topItems

    • Workspace API: Access to filters, calculated metrics, projects

    • Data Views: Read access to configured data views

Step 3: Verify OAuth Scopes

In the API credential configuration, verify these scopes are enabled:

  • openid

  • AdobeID

  • read_organizations

  • additional_info.projectedProductContext

  • cja.reporting ← CRITICAL

  • cja.workspace ← CRITICAL

Step 4: Generate New Credentials (if needed)

If updating an existing credential doesn't enable reporting access:

  1. Create a new OAuth Server-to-Server credential

  2. Add CJA API as a service

  3. Select a Product Profile with full Reporting API access

  4. Copy the new Client ID and Client Secret to your .env file

Example Queries and Expected Results

Session Analysis

Query:

Show me session count in a bar chart for the last 30 days

What Happens:

  1. Claude identifies you want session metrics over time

  2. Calls cja_get_trended_report or cja_run_report with:

    • Metric: sessions or visits

    • Date range: Last 30 days

    • Granularity: day

  3. Formats results as a text-based bar chart or table

  4. Returns daily session counts with visualization

Expected Output:

Session Count - Last 30 Days

Oct 1  ████████████████ 1,245
Oct 2  ██████████████ 1,108
Oct 3  ███████████████ 1,189
...
Oct 30 ████████████████████ 1,523

Total Sessions: 38,420
Average: 1,281 sessions/day
Peak: Oct 30 (1,523 sessions)

Top Pages Analysis

Query:

What are the top 10 pages by page views this month?

What Happens:

  1. Calls cja_get_top_items with:

    • Dimension: page or pageName

    • Metric: pageviews

    • Date range: This month

    • Limit: 10

  2. Returns ranked list of pages

Expected Output:

Top 10 Pages by Page Views - October 2025

1. /home                    15,234 views
2. /products                 8,901 views
3. /about                    6,543 views
4. /contact                  4,321 views
5. /blog/article-123         3,987 views
6. /pricing                  3,456 views
7. /features                 2,890 views
8. /blog                     2,543 views
9. /documentation            2,234 views
10. /support                 1,987 views

Total: 52,096 page views

Conversion Funnel

Query:

Show me the checkout funnel conversion rates for last week

What Happens:

  1. Calls cja_get_funnel_analysis with predefined checkout steps

  2. Or calls cja_run_report multiple times for each funnel step

  3. Calculates drop-off rates between steps

Expected Output:

Checkout Funnel - Last 7 Days

Step 1: Product Page     → 10,000 visitors (100.0%)
         ↓ 45.0%
Step 2: Add to Cart      →  4,500 visitors ( 45.0%)
         ↓ 66.7%
Step 3: Checkout Started →  3,000 visitors ( 30.0%)
         ↓ 50.0%
Step 4: Payment Info     →  1,500 visitors ( 15.0%)
         ↓ 80.0%
Step 5: Purchase         →  1,200 visitors ( 12.0%)

Overall Conversion Rate: 12.0%
Biggest Drop-off: Product Page → Add to Cart (55%)

Marketing Attribution

Query:

Show me first-touch attribution for conversions in the last 14 days

What Happens:

  1. Calls cja_get_attribution_analysis with:

    • Attribution model: first_touch

    • Success event: orders or conversions

    • Date range: Last 14 days

  2. Returns marketing channel credit distribution

Expected Output:

First-Touch Attribution - Last 14 Days
Total Conversions: 450

Channel              Conversions    % of Total    Revenue
──────────────────────────────────────────────────────────
Organic Search            180         40.0%      $45,000
Paid Search               135         30.0%      $33,750
Direct                     68         15.1%      $17,000
Email                      45         10.0%      $11,250
Social Media               22          4.9%       $5,500

Top First-Touch Channel: Organic Search
Highest Revenue/Conversion: Paid Search ($250 avg)

Available MCP Tools

Core Reporting

  • cja_run_report - Run custom analytics reports

  • cja_get_top_items - Get top-performing items for a dimension

  • cja_get_trended_report - Get time-series trends

  • cja_get_breakdown_report - Get multi-dimensional breakdowns

Metadata

  • cja_list_dimensions - List available dimensions

  • cja_list_metrics - List available metrics

  • cja_list_calculated_metrics - List calculated metrics

  • cja_list_filters - List filters/segments

  • cja_list_date_ranges - List predefined date ranges

  • cja_get_dataview_info - Get data view configuration

Advanced Analytics

  • cja_search_dimension_items - Search for dimension values

  • cja_get_sessions_data - Analyze session metrics

  • cja_get_conversions_data - Analyze conversion events

  • cja_get_attribution_analysis - Run attribution models

  • cja_get_funnel_analysis - Analyze conversion funnels

License

MIT License - see LICENSE file for details

Support

For issues or questions:

Available Tools

16 tools
cja_create_calculated_metricA

Create a new calculated metric in CJA.

Create a custom metric with formulas and functions that can be used in reports. IMPORTANT: Validate the definition first using cja_validate_calculated_metric.

Args: name: Metric name (required). definition: Metric definition with formula (required). Should have 'func': 'calc-metric', 'formula': {...}, 'version': [1,0,0]. description: Optional metric description. metric_type: Type: 'decimal', 'percent', 'currency', or 'time' (default 'decimal'). polarity: Optional 'positive' or 'negative' (indicates if higher values are better/worse). precision: Optional decimal places for display (0-10). dataview_id: Optional data view ID (uses configured default if not provided).

Returns: Dictionary with created calculated metric details including assigned ID.

Example queries: - "Create a calculated metric named 'Conversion Rate'" - "Make a new metric that divides revenue by orders" - "Create a metric for visits per visitor"

Inputs: name (required), definition (required), description, metric_type, +3 more.

cja_create_segmentA

Create a new segment in CJA.

This tool creates a new segment/filter that can be used in reports. Segment definitions use a JSON structure to define filtering rules.

IMPORTANT: Segment definitions are complex. Best practice:

  1. Create a template segment in the CJA UI

  2. Use cja_get_segment_details to see its definition structure

  3. Modify the definition as needed

  4. Use cja_validate_segment before creating

Args: name: Segment name (required). definition: Segment definition object with container and rules (required). description: Optional segment description. dataview_id: Optional data view ID (uses configured default if not provided).

Returns: Dictionary with created segment including assigned ID.

Example queries: - "Create a segment for mobile users" - "Make a new filter for high-value customers"

Example definition (mobile users): { "container": { "func": "segment", "context": "hits", "pred": { "func": "exists", "val": {"func": "attr", "name": "variables/mobiledevicetype"} } }, "func": "segment-def", "version": [1, 0, 0] }

Inputs: name (required), definition (required), description, dataview_id.

cja_get_calculated_metric_detailsA

Get detailed information about a specific calculated metric.

Retrieve complete details about a calculated metric including its definition/formula. This is useful for understanding how a metric is calculated or copying definitions.

Args: metric_id: Calculated metric ID to retrieve (required). expansion: Optional comma-delimited fields: 'definition', 'tags', 'usedIn', 'compatibility'.

Returns: Dictionary with calculated metric details and formula definition.

Example queries: - "Show me the formula for calculated metric a5066209" - "Get definition for the conversion rate metric" - "What's the formula for metric ID 12345?"

Inputs: metric_id (required), expansion.

cja_get_dataview_infoA

Get detailed information about a CJA data view.

This tool retrieves configuration and metadata for the data view, including its name, description, owner, and component counts.

Args: dataview_id: Optional data view ID (uses configured default if not provided). expansion: Optional additional fields to include (e.g., 'components').

Returns: Dictionary with data view configuration and metadata.

Example queries: - "What data view am I using?" - "Show me information about the current data view" - "What's configured in my data view?"

Inputs: dataview_id, expansion.

cja_get_segment_detailsA

Get detailed information about a specific segment.

This tool retrieves complete details about a segment including its definition, which shows the exact logic and rules used to filter data.

Args: segment_id: Segment ID to retrieve. expansion: Additional fields to include: 'definition', 'tags', 'compatibility'.

Returns: Dictionary with complete segment information.

Example queries: - "Show me the definition of segment s300000022_5bb7c94e80f0073611afb35c" - "Get details for the Mobile Users segment" - "What's the logic in segment XYZ?"

Inputs: segment_id (required), expansion.

cja_get_top_itemsA

Get top N items for a dimension ranked by a metric.

This tool is optimized for finding the top performing dimension items based on a single metric, such as top pages by visits, top products by revenue, etc.

Args: dimension: Dimension ID (e.g., 'variables/page', 'variables/product'). metric: Metric ID to rank by (e.g., 'metrics/visits', 'metrics/revenue'). start_date: Start date in YYYY-MM-DD format. end_date: End date in YYYY-MM-DD format. limit: Number of top items to return (default: 10, max: 500). dataview_id: Optional data view ID (uses configured default if not provided).

Returns: Dictionary with top dimension items and their metric values.

Example queries: - "What are the top 10 pages by visits this week?" - "Show me the top 20 products by revenue last month" - "Which marketing channels drove the most conversions?"

Inputs: dimension (required), metric (required), start_date (required), end_date (required), +2 more.

cja_list_calculated_metricsA

List calculated metrics in CJA.

Retrieve calculated metrics (custom formulas) that can be used in reports. You can filter by name, tags, and share type.

Args: name: Optional filter by metric name (partial match). tag_names: Optional comma-delimited tag names to filter by. include_type: Optional 'shared', 'all', or 'templates' to include additional metrics. limit: Maximum results per page (1-1000, default 10). page: Page number for pagination (0-indexed, default 0). expansion: Optional comma-delimited fields: 'definition', 'tags', 'usedIn', 'compatibility'. dataview_id: Optional data view ID to filter metrics (uses configured default if not provided).

Returns: Dictionary with list of calculated metrics and total count.

Example queries: - "Show me all calculated metrics" - "List calculated metrics containing 'conversion' in the name" - "Get calculated metrics with their definitions"

Inputs: name, tag_names, include_type, limit, +3 more.

cja_list_dimensionsA

List all available dimensions in the CJA data view.

Dimensions are attributes that can be used to break down and categorize your data, such as page names, product categories, marketing channels, date/time components, etc.

Args: dataview_id: Optional data view ID (uses configured default if not provided). expansion: Optional additional fields to include (e.g., 'tags,approved').

Returns: Dictionary with dimensions list and total count.

Example queries: - "What dimensions are available in my data view?" - "List all dimensions I can use for analysis" - "Show me the available breakdowns"

Inputs: dataview_id, expansion.

cja_list_metricsA

List all available metrics in the CJA data view.

Metrics are quantitative measurements of your data, such as visits, page views, revenue, conversion rates, time spent, etc.

Args: dataview_id: Optional data view ID (uses configured default if not provided). expansion: Optional additional fields to include.

Returns: Dictionary with metrics list and total count.

Example queries: - "What metrics can I measure?" - "List all available metrics" - "Show me metrics for measuring website performance"

Inputs: dataview_id, expansion.

cja_list_segmentsA

List all available segments/filters in CJA.

Segments (also called filters in CJA) are reusable components that filter data in reports and analysis. This tool retrieves all segments you have access to.

Args: dataview_id: Optional data view ID to filter segments (uses configured default if not provided). name: Filter segments by name (partial match). tag_names: Comma-delimited list of tag names to filter by. include_type: Include additional segments: 'shared', 'all', 'templates'. limit: Number of results per page (default: 10, max: 1000). page: Page number, 0-indexed (default: 0). expansion: Additional fields to include: 'definition', 'tags', 'compatibility', 'ownerFullName'.

Returns: Dictionary with segments list and metadata.

Example queries: - "List all available segments" - "Show me segments with 'mobile' in the name" - "What filters are tagged with 'marketing'?" - "List all shared segments"

Inputs: dataview_id, name, tag_names, include_type, +3 more.

cja_run_breakdown_reportA

Run a multi-dimensional breakdown report.

This tool performs breakdown analysis where you analyze a primary dimension and further break it down by a secondary dimension. For example, analyze pages and break them down by device type to understand device distribution per page.

Args: primary_dimension: Primary dimension ID (e.g., 'variables/page', 'variables/campaign'). breakdown_dimension: Dimension to break down by (e.g., 'variables/mobiledevicetype'). metrics: List of metric IDs to analyze. start_date: Start date in YYYY-MM-DD format. end_date: End date in YYYY-MM-DD format. limit: Maximum number of primary dimension items (default: 10, max: 500). breakdown_limit: Maximum breakdown items per primary item (default: 5, max: 50). segment_ids: Optional list of segment IDs to filter the report. dataview_id: Optional data view ID (uses configured default if not provided).

Returns: Dictionary with nested breakdown report results.

Example queries: - "Break down top pages by device type" - "Show me campaigns broken down by browser for last month" - "Analyze product performance by marketing channel"

Inputs: primary_dimension (required), breakdown_dimension (required), metrics (required), start_date (required), +5 more.

cja_run_reportA

Run a CJA report with specified dimension and metrics over a date range.

This is the primary tool for analyzing data. It breaks down one or more metrics by a dimension over a specified time period.

IMPORTANT: Before calling this tool, check the 'cja://quick-reference' resource for common dimension and metric IDs. For daily trends, use 'variables/daterangeday'. For sessions, use 'metrics/visits'. The resources provide commonly used IDs.

Args: dimension: Dimension ID to break down (e.g., 'variables/daterangeday', 'variables/page'). metrics: List of metric IDs to measure (e.g., ['metrics/visits', 'metrics/pageviews']). start_date: Start date in YYYY-MM-DD format. end_date: End date in YYYY-MM-DD format. limit: Maximum number of dimension items to return (default: 10, max: 50000). dataview_id: Optional data view ID (uses configured default if not provided).

Returns: Dictionary with report data including dimension items and metric values.

Common patterns (check cja://quick-reference resource for more): - Daily sessions: dimension='variables/daterangeday', metrics=['metrics/visits'] - Top pages: dimension='variables/page', metrics=['metrics/pageviews'] - Device breakdown: dimension='variables/mobiledevicetype', metrics=['metrics/visits']

Example queries: - "Show me daily visits for January 2024" - "What are the top pages by pageviews last month?" - "Analyze sessions by device type for Q1"

Inputs: dimension (required), metrics (required), start_date (required), end_date (required), +2 more.

cja_run_trended_reportA

Run a time-series trend report.

This tool analyzes how metrics change over time at a specified granularity (hourly, daily, weekly, monthly). Optionally break down trends by a dimension.

Args: metrics: List of metric IDs to trend over time. start_date: Start date in YYYY-MM-DD format. end_date: End date in YYYY-MM-DD format. granularity: Time granularity - 'hour', 'day', 'week', or 'month' (default: 'day'). dimension: Optional dimension to break down the trend (e.g., 'variables/mobiledevicetype'). dimension_limit: Maximum dimension items if dimension specified (default: 5, max: 50). segment_ids: Optional list of segment IDs to filter the report. dataview_id: Optional data view ID (uses configured default if not provided).

Returns: Dictionary with time-series trend data.

Example queries: - "Show me daily visits trend for last 30 days" - "Trend pageviews by hour for yesterday" - "Show weekly revenue trend broken down by device type" - "Monthly orders trend for Q1 2024"

Inputs: metrics (required), start_date (required), end_date (required), granularity, +4 more.

cja_search_dimension_itemsA

Search for dimension items matching a search term.

This tool searches within a dimension's values to find items containing the search term. Useful for finding specific pages, products, campaigns, etc.

Args: dimension: Dimension ID to search within (e.g., 'variables/page', 'variables/product'). search_term: Search term to find matching dimension items. start_date: Optional start date to scope search results (YYYY-MM-DD format). end_date: Optional end date to scope search results (YYYY-MM-DD format). limit: Maximum number of matching items to return (default: 100, max: 1000). dataview_id: Optional data view ID (uses configured default if not provided).

Returns: Dictionary with matching dimension items.

Example queries: - "Find all pages containing 'checkout'" - "Search for products with 'pro' in the name" - "Which campaigns contain 'summer'?" - "Find pages with 'login' that had activity last week"

Inputs: dimension (required), search_term (required), start_date, end_date, +2 more.

cja_validate_calculated_metricA

Validate a calculated metric definition before creating or updating.

Check if a calculated metric definition is syntactically correct and compatible with the data view. Always use this before creating a new metric.

Args: name: Metric name for validation (required). definition: Metric definition to validate (required). metric_type: Type: 'decimal', 'percent', 'currency', or 'time' (default 'decimal'). description: Optional metric description for validation. dataview_id: Optional data view ID to validate against (uses configured default if not provided).

Returns: Dictionary with validation result, metrics used, and functions detected.

Example queries: - "Validate this calculated metric definition before I create it" - "Check if this metric formula is valid" - "Is this calculated metric definition compatible?"

Inputs: name (required), definition (required), metric_type, description, +1 more.

cja_validate_segmentA

Validate a segment definition before creating or updating.

This tool checks if a segment definition is syntactically correct and compatible with the specified data view. Always use this before creating a new segment.

Args: definition: Segment definition to validate (required). dataview_id: Optional data view ID to validate against (uses configured default if not provided).

Returns: Dictionary with validation result and compatibility information.

Example queries: - "Validate this segment definition before I create it" - "Check if this filter definition is valid" - "Is this segment compatible with my data view?"

Inputs: definition (required), dataview_id.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 16 tools

    Disambiguation5/5

    Each tool targets a distinct resource or action. CRUD-like tools are separated per entity (calculated metrics vs. segments), report tools have different purposes (general, breakdown, trend, top items), and metadata tools (list dimensions, metrics, dataview) are clearly distinct.

    Naming Consistency5/5

    All tools follow the consistent 'cja_verb_noun' pattern in snake_case, e.g., cja_create_calculated_metric, cja_run_report, cja_list_dimensions. No mixing of conventions.

    Tool Count5/5

    16 tools cover the core functionalities of CJA: CRUD for metrics and segments, multiple report types, dimension/metadata discovery. The count feels right for a focused analytics server.

    Completeness4/5

    Covers creation, retrieval, listing, and validation for metrics/segments, plus various report types. Missing update/delete operations for metrics and segments, but core workflows are supported.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      MCP server that enables AI agents (Claude Code) to manage Criteo campaigns, ad sets, creatives, audiences, and reports via natural language.
      -
    • F
      license
      B
      quality
      D
      maintenance
      A platform-agnostic MCP server that connects Claude to campaign data, institutional knowledge, and historical performance for paid media teams, enabling automated analysis, reporting, and debugging.
      73
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that provides product and web analytics capabilities, allowing AI coding assistants to query funnels, retention, trends, feature flags, A/B tests, and more in natural language.
      4
      MIT