How to Use the Reportei MCP in LlamaIndex

Q: Can LlamaIndex query specific client profiles using Reportei?

Yes. The agent uses listclients to find the correct client record. It then calls getclient to retrieve specific configuration details, which are converted into document nodes for semantic querying.

Q: How does the Reportei MCP Server improve RAG accuracy in LlamaIndex?

It provides raw, structured JSON data directly from getreporteimetrics. This structured input prevents the model from hallucinating numbers, as the context window is populated with real-time performance metrics.

Q: Can I index historical marketing projects with LlamaIndex?

Yes. Your ingestion pipeline can call listreporteiprojects to map out all active marketing campaigns. This metadata is tagged to your vector nodes, allowing you to filter search queries by specific project IDs.

Index live Google and Facebook marketing metrics into LlamaIndex to query performance data using natural language.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Reportei MCP to LlamaIndex

Create your Vinkius account to connect Reportei to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Reportei with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Ground LlamaIndex RAG applications in live marketing data

This MCP Server connects your LlamaIndex pipelines directly to live marketing performance metrics. Stop letting your LLM guess how your ad campaigns are performing. You can feed live results from `get_reportei_metrics` directly into your vector index. Your agent queries the index to find performance trends. This ensures that any answer about ad spend or conversion rates is grounded in actual API data rather than outdated training sets.

Build a searchable index of historical client reports

This Reportei integration lets LlamaIndex build a searchable, structured index of your historical marketing reports. The framework can fetch past documents using `list_reportei_reports` and parse the details with `get_report_details` to build a semantic search index. Analysts can ask natural language questions about past performance across multiple projects. The framework matches the query against the indexed report data to give you instant, accurate answers.

Map client timelines to semantic vector stores

This MCP Server exposes client timeline events directly to your LlamaIndex RAG pipelines. The agent pulls historical milestones using `list_reportei_timeline` and converts them into searchable text nodes. When you need to prepare for a meeting, your agent searches this index to compile a summary of recent changes. You can also log new milestones using `add_reportei_event` directly from your query pipeline.

Setup guide

Set up Reportei 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 Reportei 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 Reportei tools.",
)
response = await agent.run("List recent Reportei 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 Reportei. 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 Reportei 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 Reportei MCP in LlamaIndex

Initialize the BasicMCPClient with your Vinkius endpoint and wrap it in McpToolSpec. You can then call to_tool_list_async to get the tools and pass them to your FunctionAgent.

Yes. The agent uses list_clients to find the correct client record. It then calls get_client to retrieve specific configuration details, which are converted into document nodes for semantic querying.

It provides raw, structured JSON data directly from get_reportei_metrics. This structured input prevents the model from hallucinating numbers, as the context window is populated with real-time performance metrics.

Yes. Your ingestion pipeline can call list_reportei_projects to map out all active marketing campaigns. This metadata is tagged to your vector nodes, allowing you to filter search queries by specific project IDs.

The integration only accesses read-only performance metrics and metadata. No raw access credentials or password hashes ever leave the secure Vinkius V8 sandbox, protecting your client account security.

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