Can it retrieve all form submission data (Leads) for a specific landing page in one go?

Absolutely. Just instruct the agent using the 'list_page_leads' capability, feeding it the specific landing page ID. It directly taps the records returning JSON-wrapped metadata of exactly what your visitors typed in.

How can I check the performance and stats of a live landing page quickly?

Simply ask the agent to fetch the page statistics using 'get_page_statistics' with its respective ID. Data elements like bounce rates, overall views vs conversions naturally return into the AI context mapping easy charts.

Can it query sub-accounts dynamically finding out assigned domains on larger enterprise accounts?

Yes. First call 'list_sub_accounts' to get raw IDs, then orchestrate 'list_sub_account_domains' recursively across those IDs. In one prompt, your AI audits the entire organizational deployment topology natively.

Unbounce MCP Server for LlamaIndex 4 tools — connect in under 2 minutes

Name: Unbounce
Availability: InStock
Author: Vinkius

docs.llamaindex.ai/en/stable/module_guides/tools/mcp

Built by Vinkius GDPR 4 Tools Framework

LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Unbounce as an MCP tool provider through the Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    agent = FunctionAgent(
        tools=tools,
        llm=OpenAI(model="gpt-4o"),
        system_prompt=(
            "You are an assistant with access to Unbounce. "
            "You have 4 tools available."
        ),
    )

    response = await agent.run(
        "What tools are available in Unbounce?"
    )
    print(response)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Unbounce MCP Server

Connect your Unbounce marketing workflows to any AI agent and take full enterprise control over global landing pages, captured leads routing, and real-time conversion monitoring natively via conversational commands.

LlamaIndex agents combine Unbounce tool responses with indexed documents for comprehensive, grounded answers. Connect 4 tools through the Vinkius and query live data alongside vector stores and SQL databases in a single turn — ideal for hybrid search, data enrichment, and analytical workflows.

What you can do

Project & Sub-Account Control — Interrogate your organization's hierarchy grouping, natively verifying assigned domains before pushing any pages live
Real-Time Lead Extraction — Fetch form submission pipelines continuously directly from targeted pages without battling CSV exports
Variant Auditing — Read A/B testing splits mapped across single pages to identify statistically significant conversions rapidly
Lead Obliteration — Trigger raw data-privacy deletions directly across specific captured accounts dropping rogue leads off the servers

The Unbounce MCP Server exposes 4 tools through the Vinkius. Connect it to LlamaIndex in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Unbounce to LlamaIndex via MCP

Follow these steps to integrate the Unbounce MCP Server with LlamaIndex.

Install dependencies

Run pip install llama-index-tools-mcp llama-index-llms-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 4 tools from Unbounce

Why Use LlamaIndex with the Unbounce MCP Server

LlamaIndex provides unique advantages when paired with Unbounce through the Model Context Protocol.

Data-first architecture: LlamaIndex agents combine Unbounce tool responses with indexed documents for comprehensive, grounded answers

Query pipeline framework lets you chain Unbounce tool calls with transformations, filters, and re-rankers in a typed pipeline

Multi-source reasoning: agents can query Unbounce, a vector store, and a SQL database in a single turn and synthesize results

Observability integrations show exactly what Unbounce tools were called, what data was returned, and how it influenced the final answer

Unbounce + LlamaIndex Use Cases

Practical scenarios where LlamaIndex combined with the Unbounce MCP Server delivers measurable value.

Hybrid search: combine Unbounce real-time data with embedded document indexes for answers that are both current and comprehensive

Data enrichment: query Unbounce to augment indexed data with live information before generating user-facing responses

Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying Unbounce for fresh data

Analytical workflows: chain Unbounce queries with LlamaIndex's data connectors to build multi-source analytical reports

Unbounce MCP Tools for LlamaIndex (4)

These 4 tools become available when you connect Unbounce to LlamaIndex via MCP:

domains

List custom domains configured in the account

leads

List leads/submissions for a specific landing page

pages

List landing pages in Unbounce

sub_accounts

List sub-accounts available to the user

Example Prompts for Unbounce in LlamaIndex

Ready-to-use prompts you can give your LlamaIndex agent to start working with Unbounce immediately.

"Please list the verified domains available for publication underneath the specific main active sub-account."

"Summarize the conversion metrics and variant splits for the 'Enterprise Launch Q3' LP ID."

"Isolate the exact form submission metadata payload for lead ID 7709xxv-1123."

Troubleshooting Unbounce MCP Server with LlamaIndex

Common issues when connecting Unbounce to LlamaIndex through the Vinkius, and how to resolve them.

BasicMCPClient not found

Install: pip install llama-index-tools-mcp

Unbounce + LlamaIndex FAQ

Common questions about integrating Unbounce MCP Server with LlamaIndex.

How does LlamaIndex connect to MCP servers?

Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.

Can I combine MCP tools with vector stores?

Yes. LlamaIndex agents can query Unbounce tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.