How to Use the IPQualityScore (IPQS) MCP in LlamaIndex

Q: How do I index IPQualityScore (IPQS) threat logs into a LlamaIndex vector store?

You run listreports or listfraud to retrieve the latest security events. This MCP server returns structured JSON which LlamaIndex converts into Document objects, ready for embedding and semantic search.

Q: Does this IPQualityScore (IPQS) integration support LlamaIndex's asynchronous tool execution?

Yes. You can call totoollistasync() on the MCP tool spec, allowing LlamaIndex to run checks like emaillookup and phonelookup in parallel to minimize pipeline latency.

Q: How do I limit which IPQS tools are visible to my LlamaIndex agent?

You use the allowedtools filter when initializing the client. This lets you restrict the agent to just urllookup or iplookup depending on what your specific pipeline needs.

Index live fraud data and protect your RAG pipelines using IPQualityScore (IPQS) and LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IPQualityScore (IPQS) MCP to LlamaIndex

Create your Vinkius account to connect IPQualityScore (IPQS) 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 IPQualityScore (IPQS) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index historical fraud events for semantic search

The `list_fraud` tool retrieves your organization's logged security triggers and feeds them directly into LlamaIndex vector stores. Your RAG pipeline can then query this historical threat data to identify recurring attack patterns. This lets your agent search past incidents semantically instead of manually parsing database logs. By converting raw API outputs into searchable document nodes, LlamaIndex makes it easy to compare current user behavior against known bad actors.

Prevent bad data from entering your LlamaIndex knowledge base

The `ip_lookup` tool screens incoming user data sources for proxy or VPN activity before LlamaIndex indexes them. If a user tries to upload documents from a flagged IP, your agent can reject the ingestion. Using this MCP server tool ensures your retrieval-augmented generation index remains clean and untainted by malicious actors. You get reliable data ingestion by screening the source IP before any parsing or embedding happens.

Audit user-submitted links before indexing

The `url_lookup` tool checks the safety of external links extracted from documents before LlamaIndex adds them to your index. This prevents your RAG system from recommending malicious or phishing URLs to end-users during retrieval. Your pipeline automatically runs this check on every discovered link during the document ingestion phase. By storing only verified URLs, you protect your users from visiting compromised sites suggested by your search index.

Setup guide

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

You run `list_reports` or `list_fraud` to retrieve the latest security events. This MCP server returns structured JSON which LlamaIndex converts into Document objects, ready for embedding and semantic search.

Yes. You can wrap your ingestion pipeline in a function that calls `ip_lookup` first. If the fraud score is high, LlamaIndex halts the document parsing process to protect your database.

Yes. You can call `to_tool_list_async()` on the MCP tool spec, allowing LlamaIndex to run checks like `email_lookup` and `phone_lookup` in parallel to minimize pipeline latency.

You use the `allowed_tools` filter when initializing the client. This lets you restrict the agent to just `url_lookup` or `ip_lookup` depending on what your specific pipeline needs.

All phone numbers and URLs queried through this MCP server are processed in ephemeral V8 isolates. The data is transmitted securely to IPQS via TLS 1.3, and no persistent logs of these identifiers are kept on the Vinkius hosting layer.

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