MCP Ip2location Io

IP2Location.io MCP server

IP2Location.io MCP Server is a Model Context Protocol (MCP) server that enables MCP-compatible AI clients to perform IP address geolocation and network intelligence lookups using the IP2Location.io API.

Give it an IPv4 or IPv6 address and the MCP server can retrieve information such as geographic location, ASN, ISP, domain, network type, and proxy information, depending on your IP2Location.io API plan.

This makes it useful for IP investigation, network troubleshooting, traffic analysis, localization, security analysis, and enriching IP addresses found in logs or other datasets.

Features

• Comprehensive Geolocation Data: Retrieve country, region, city, ZIP/postal code, latitude, longitude, time zone, and other location information.
• ASN Lookup: Identify the Autonomous System Number (ASN) and Autonomous System (AS) associated with an IP address.
• Network Intelligence: Retrieve information such as ISP, domain, connection speed, usage type, and other network attributes depending on your plan.
• Proxy and Security Information: Detect proxy-related information and, on supported plans, additional VPN, Tor, data center, threat, and fraud information.
• IPv4 and IPv6 Support: Query both IPv4 and IPv6 addresses.
• Bulk IP Lookup: Send multiple IP addresses in one prompt and automatically use the IP2Location.io Bulk API when available.
• MCP Integration: Use IP intelligence directly from MCP-compatible AI applications.
• Asynchronous Requests: Uses httpx for asynchronous API requests.

[!NOTE]

The fields returned by IP2Location.io depend on your API subscription plan.

Requirements

There are two ways to use this MCP server.

Cloud-hosted MCP server

Recommended when you want to connect directly to the hosted IP2Location.io MCP server.

You can connect in either of two ways:

• Direct HTTP connection: Your MCP client supports remote (streamable HTTP) MCP servers. No extra software is required.
• Via `npx`: Your MCP client only supports local (stdio) servers. This uses the mcp-remote package to bridge to the hosted server.

You need:

• An MCP-compatible client such as Claude Desktop
• An IP2Location.io API key
• Node.js / npx (only for the npx connection method)

Local MCP server

Use this option when you want to run the MCP server locally.

You need:

• Python 3.13 or later
• uv
• An MCP-compatible client such as Claude Desktop
• An IP2Location.io API key

You can sign up for a free IP2Location.io API key. The Free plan provides up to 50,000 IP Geolocation API queries per month.

The underlying IP2Location.io REST API also supports limited keyless access of up to 1,000 queries per day. For this MCP server, configuring an API key is recommended and is used in the setup examples below.

Setup

You can use this MCP server in Claude Desktop in either of the following ways:

• Cloud-hosted MCP server: Recommended if you want to connect directly to the hosted IP2Location.io MCP server.
• Local MCP server: Use this if you want to download and run the original MCP server on your own machine.

Option 1: Cloud-hosted MCP server

Follow these steps to connect Claude Desktop to the hosted IP2Location.io MCP server.

1. Make sure you have installed Claude Desktop. If you have not installed it yet, download it from here for Windows and macOS, or follow this guide for Linux users.
2. Open the claude_desktop_config.json file in your choice of editor. If you do not have one yet, follow this guide to create one.
3. Add one of the configurations below, depending on how you want to connect.

Method A: Direct HTTP connection

Use this if your MCP client supports remote servers over HTTP. No Node.js or npx is needed.

{

"mcpServers": { "ip2location": { "type": "http", "url": "https://mcp.ip2location.io/", "headers": { "X-API-Key": "YOUR_API_KEY" } } } }

If your client is configured from the command line, such as Claude Code, you can add the server with:

claude mcp add --transport http ip2location https://mcp.ip2location.io/ --header "X-API-Key: YOUR_API_KEY"

Method B: Connection through npx

Use this if your MCP client only supports local (stdio) servers. The mcp-remote package runs locally and forwards requests to the hosted server.

{

"mcpServers": { "ip2location": { "command": "npx", "args": [ "-y", "mcp-remote@latest", "https://mcp.ip2location.io/", "--header", "X-API-Key:YOUR_API_KEY" ] } } }

1. Replace YOUR_API_KEY with your actual IP2Location.io API key. To get your API key, log in to your dashboard.
2. Restart Claude Desktop after saving the changes, and you should see the MCP server appear in the Connectors menu.

Option 2: Local MCP server

Follow these steps if you prefer to run the MCP server locally.

1. Set up the uv package manager. You can refer to the guide to do so.
2. Make sure you have installed Claude Desktop. If you have not installed it yet, download it from here for Windows and macOS, or follow this guide for Linux users.
3. Open the claude_desktop_config.json file in your choice of editor. If you do not have one yet, follow this guide to create one.
4. Add the following to your claude_desktop_config.json:

{

"mcpServers": { "ip2locationio": { "command": "uvx", "args": [ "mcp-ip2location-io" ], "env": { "IP2LOCATION_API_KEY": " " } } } }

1. To get your API key, log in to your dashboard. Replace in the example above with your actual API key.
2. Restart Claude Desktop after saving the changes, and you should see it appear in the Connectors menu.

Framework Integration

The MCP server can also be used from Python agent frameworks. The examples below connect to the hosted server over HTTP. To use the local server instead, connect with the stdio command uvx and the argument mcp-ip2location-io, and pass IP2LOCATION_API_KEY as an environment variable.

Each example reads the API key from the IP2LOCATION_API_KEY environment variable, so the key never appears in your source code.

LangChain

LangChain includes MCP support in the langchain.mcp namespace, which requires LangChain 1.4 or later.

pip install "langchain[mcp]" langchain-anthropic

import asyncio

import os

from fastmcp.client.transports import StreamableHttpTransport from langchain.agents import create_agent from langchain.mcp import MCPAdapter

async def main(): transport = StreamableHttpTransport( "https://mcp.ip2location.io/", headers={"X-API-Key": os.environ["IP2LOCATION_API_KEY"]}, )

async with MCPAdapter(transport) as adapter: tools = await adapter.list_tools()

agent = create_agent("anthropic:claude-sonnet-5", tools) result = await agent.ainvoke({"messages": "Where is 8.8.8.8 located?"}) print(result"messages".content)

if name == "main": asyncio.run(main())

MCPAdapter accepts the server URL directly, but the StreamableHttpTransport object is passed here so the X-API-Key header can be set.

LlamaIndex

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

import asyncio

import os

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

async def main(): client = BasicMCPClient( "https://mcp.ip2location.io/", headers={"X-API-Key": os.environ["IP2LOCATION_API_KEY"]}, )

tools = await McpToolSpec(client=client).to_tool_list_async()

agent = FunctionAgent( tools=tools, llm=OpenAI(model="gpt-5-mini"), system_prompt="You are a helpful assistant that looks up IP addresses.", )

response = await agent.run("Where is 8.8.8.8 located?") print(response)

if name == "main": asyncio.run(main())

CrewAI

CrewAI reads MCP servers from the mcps field on an agent. This requires the mcp package to be installed alongside CrewAI.

pip install crewai mcp

import os

from crewai import Agent, Crew, Process, Task from crewai.mcp import MCPServerHTTP

ip_agent = Agent( role="IP Intelligence Analyst", goal="Look up geolocation and network information for an IP address.", backstory="An analyst who checks IP addresses against IP2Location.io.", mcps=[ MCPServerHTTP( url="https://mcp.ip2location.io/", headers={"X-API-Key": os.environ["IP2LOCATION_API_KEY"]}, ) ], )

task = Task( description="Find the geolocation of 8.8.8.8 and summarize the result.", expected_output="A short summary of the IP address location and network data.", agent=ip_agent, )

crew = Crew(agents=[ip_agent], tasks=[task], process=Process.sequential) print(crew.kickoff())

On CrewAI versions that do not support the mcps field, install crewai-tools[mcp] and wrap the server with MCPServerAdapter from crewai_tools instead.

Usage

Once the MCP server is connected, ask your MCP client questions about an IPv4 or IPv6 address using natural language. Just enter your query about the IP in a chat in Claude Desktop.

IP geolocation

Where is the location of (IP)?

Where is (IP) located?

What is the latitude and longitude of (IP)?

For instance, below is the result of the IP 8.8.8.8:

In Claude Desktop, the model will automatically generate the output based on the result returned by IP2Location.io MCP server.

Proxy and security lookup

Depending on the IP2Location.io plan being used:

Is this IP address a proxy: 8.8.8.8?

Multiple IP addresses

You can also utilize IP2Location.io Bulk IP Geolocation API to query for multiple IP addresses.

Look up 8.8.8.8 8.8.6.6 9.9.9.9

The MCP server detects multiple IP addresses and sends them to the IP2Location.io Bulk API when possible.

IP addresses can be separated by commas, spaces, or new lines.

[!NOTE]

IP2Location.io Bulk IP Geolocation API access requires an eligible paid plan.

Environment Variable

IP2LOCATION_API_KEY

Your IP2Location.io API key IP2LOCATION_API_KEY.

The Free plan currently provides up to 50,000 IP Geolocation API queries per month and access to basic IP information.

Paid plans provide higher query quotas and additional attributes.

You can sign up for a free API key, or subscribe higher plan for comprehensive geo-ip data.

Do not commit your API key to a public Git repository.

MCP Tool

get_geolocation

Description

• Fet