How to Use the Adobe Customer Journey Analytics (CJA) MCP in LlamaIndex

Q: Can LlamaIndex query Adobe Customer Journey Analytics (CJA) without hallucinations?

Yes, because the agent pulls live metrics using getdataviewmetrics and getreport. The LLM only synthesizes the retrieved JSON, ensuring answers are strictly grounded in your actual Adobe data.

Q: How does LlamaIndex handle complex filters in Adobe Customer Journey Analytics (CJA)?

The agent calls listfilters to find existing journey segments, then applies them to the report query. This ensures your semantic search results respect your predefined marketing segments.

Q: Can I filter which CJA tools are exposed to my LlamaIndex agent?

Yes, you can use the allowedtools parameter during initialization to restrict access. For example, you can expose only report-reading tools while hiding configuration tools.

Index Adobe Customer Journey Analytics (CJA) data into LlamaIndex vector stores for grounded RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adobe Customer Journey Analytics (CJA) MCP to LlamaIndex

Create your Vinkius account to connect Adobe Customer Journey Analytics (CJA) to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Adobe Customer Journey Analytics (CJA) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground RAG agents with real-time CJA reports

The `get_report` tool pulls live omnichannel analytics directly into your LlamaIndex knowledge index. This turns raw journey metrics into searchable documents that your agent can query semantically. Instead of relying on static exports, your index stays updated with fresh performance data. Your queries return answers grounded in actual customer behavior rather than outdated training data.

Search across connections using this MCP Server

Running `list_connections` allows this MCP Server to discover your active Adobe Experience Platform connections. LlamaIndex indexes these connections, making your data architecture searchable. Your agent searches this index to locate where specific customer profiles are stored. You eliminate manual mapping because the system self-documents your data pipeline.

Parse metrics and dimensions for semantic queries

The `get_data_view_metrics` tool retrieves the exact definitions of your analytics variables. LlamaIndex stores these metrics in a local vector index to help the agent understand what data is available. Combined with `get_data_view_dimensions`, the system builds a semantic map of your CJA workspace. When a user asks a question, the agent matches the request to the correct dimensions without manual prompting.

Setup guide

Set up Adobe Customer Journey Analytics (CJA) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Adobe Customer Journey Analytics (CJA) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Adobe Customer Journey Analytics (CJA) tools.",
)
response = await agent.run("List recent Adobe Customer Journey Analytics (CJA) data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Adobe CJA. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Adobe Customer Journey Analytics (CJA) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Adobe Customer Journey Analytics (CJA) MCP in LlamaIndex

Use the McpToolSpec wrapper to convert the MCP Server tools into LlamaIndex tools. The output of tools like `get_report` can then be loaded directly into your vector store documents.

Yes, because the agent pulls live metrics using `get_data_view_metrics` and `get_report`. The LLM only synthesizes the retrieved JSON, ensuring answers are strictly grounded in your actual Adobe data.

The agent calls `list_filters` to find existing journey segments, then applies them to the report query. This ensures your semantic search results respect your predefined marketing segments.

Yes, you can use the allowed_tools parameter during initialization to restrict access. For example, you can expose only report-reading tools while hiding configuration tools.

All data processing happens in a zero-trust, ephemeral V8 sandbox hosted by Vinkius for this MCP Server. Your connection strings, filters, and report outputs are never cached or written to persistent disks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript