How to Use the Nmap Online MCP in LlamaIndex

Q: How do I connect Nmap Online to a LlamaIndex agent?

After pip install llama-index-tools-mcp, create a BasicMCPClient with the server URL. Then, wrap it in an McpToolSpec and call .totoollistasync() to get the tools for your agent.

Q: How does LlamaIndex handle data from Nmap Online tools like nmapscan?

LlamaIndex treats the output of each tool call as a Document. These documents, containing your scan results, can then be indexed into any supported vector store for later retrieval.

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

Yes. When you create the McpToolSpec, you can pass an allowedtools list. This lets you restrict the agent to only use specific functions, like dnslookup, while blocking others.

Q: What about data privacy with Nmap Online and LlamaIndex?

The data you send—like IPs for a geoiplookup or domains for a whoislookup—is processed in a zero-trust environment. The Vinkius MCP server handles the tool execution in an isolated session and returns the result. We never log or persist the contents of your queries or the resulting index data.

Index your network's state with LlamaIndex. Turn Nmap Online scan results into a queryable knowledge base for your RAG apps.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nmap Online MCP to LlamaIndex

Create your Vinkius account to connect Nmap Online 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 Nmap Online with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a Network Knowledge Base

LlamaIndex turns Nmap Online tool outputs into a searchable index. Run an `nmap_scan` or `list_subdomains`, and the results are automatically ingested. Now your agent's knowledge isn't just in a pre-trained model; it's grounded in the real-time state of your network. Ask questions like "Which subdomains had port 8080 open last week?" and get an answer based on actual scan data. Your agent can query past `whois_lookup` records or `traceroute` results to understand historical changes.

RAG for Security Audits

This MCP server lets you build RAG applications for security. When you ask your agent about a potential vulnerability, it doesn't just guess. It can run a `get_http_headers` check, retrieve the results from its index, and synthesize an answer based on live data. You combine static documents, like security policies, with live API data from tools like `dns_lookup`. This gives your agent the context to answer complex questions, comparing expected configurations against the actual state returned by the tools.

Query Infrastructure with LlamaIndex

Connect this MCP Server to LlamaIndex and start asking plain-English questions about your infrastructure. The `McpToolSpec` automatically makes tools like `ping_host` and `geoip_lookup` available to your query engine. No more manual queries. Your agent can translate a question like "Where is our main web server located and what's the path to it?" into a sequence of `dns_lookup`, `geoip_lookup`, and `traceroute` calls. The final answer is synthesized from the combined results.

Setup guide

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

After `pip install llama-index-tools-mcp`, create a `BasicMCPClient` with the server URL. Then, wrap it in an `McpToolSpec` and call `.to_tool_list_async()` to get the tools for your agent.

Yes, that's the primary use case. You can use a query engine to run tools like `get_page_links` and ingest the output into a vector index. Your agent can then retrieve this data to answer questions.

LlamaIndex treats the output of each tool call as a `Document`. These documents, containing your scan results, can then be indexed into any supported vector store for later retrieval.

Yes. When you create the `McpToolSpec`, you can pass an `allowed_tools` list. This lets you restrict the agent to only use specific functions, like `dns_lookup`, while blocking others.

The data you send—like IPs for a `geoip_lookup` or domains for a `whois_lookup`—is processed in a zero-trust environment. The Vinkius MCP server handles the tool execution in an isolated session and returns the result. We never log or persist the contents of your queries or the resulting index data.

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