isIPsafe
Check whether an IP address or network is malicious and report abusive IPs to isIPsafe.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"isipsafe": {
"url": "https://isipsafe.com/mcp"
}
}
}Remote endpoints
https://isipsafe.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (12)
🟢check_ip(ip, maxAgeInDays, verbose)
Reputation of one IPv4 or IPv6 address: abuse confidence score (0-100, 75+ is on the blocklist), number of reports and distinct reporters, attack categories, country, network owner (ASN), Tor exit status and a link to its page. Set verbose to include the latest reports with their comments.
Input Schema
{
"type": "object",
"properties": {
"ip": {
"description": "IPv4 or IPv6 address, e.g. 203.0.113.7",
"type": "string"
},
"maxAgeInDays": {
"default": 30,
"description": "Only count reports from the last N days",
"maximum": 365,
"minimum": 1,
"type": "integer"
},
"verbose": {
"description": "Include up to 100 recent reports with comments",
"type": "boolean"
}
},
"required": [
"ip"
],
"additionalProperties": false
}🟢get_reports(ip, maxAgeInDays, page, perPage)
The individual abuse reports filed against one address, newest first, with time, categories, comment (usually log lines) and reporter. Paginated.
Input Schema
{
"type": "object",
"properties": {
"ip": {
"description": "IPv4 or IPv6 address",
"type": "string"
},
"maxAgeInDays": {
"default": 30,
"description": "Only reports from the last N days",
"maximum": 365,
"minimum": 1,
"type": "integer"
},
"page": {
"default": 1,
"description": "Page number",
"maximum": 100000,
"minimum": 1,
"type": "integer"
},
"perPage": {
"default": 25,
"description": "Reports per page",
"maximum": 100,
"minimum": 1,
"type": "integer"
}
},
"required": [
"ip"
],
"additionalProperties": false
}🟢check_network(maxAgeInDays, network)
Every reported address inside a CIDR block (IPv4 up to /16, IPv6 up to /48), with score, report count and last report time, plus the network's owner. Use it to judge a whole hosting range or subnet.
Input Schema
{
"type": "object",
"properties": {
"maxAgeInDays": {
"default": 30,
"description": "Only count reports from the last N days",
"maximum": 365,
"minimum": 1,
"type": "integer"
},
"network": {
"description": "CIDR block, e.g. 203.0.113.0/24",
"type": "string"
}
},
"required": [
"network"
],
"additionalProperties": false
}🟡report_ip(categories, comment, ip, timestamp)
File an abuse report against an address that attacked a system you run. Needs an API key. Use category codes from list_categories (e.g. ssh,brute-force) and put the evidence (log lines, never personal data) in the comment. Each reporter can report the same address once per 15 minutes. Only report real, observed abuse.
Input Schema
{
"type": "object",
"properties": {
"categories": {
"description": "Comma-separated category codes or numeric IDs, e.g. ssh,brute-force",
"type": "string"
},
"comment": {
"description": "Evidence: what happened, ideally the relevant log lines",
"type": "string"
},
"ip": {
"description": "The attacking IPv4 or IPv6 address",
"type": "string"
},
"timestamp": {
"description": "When the attack happened, ISO 8601 (optional, defaults to now)",
"type": "string"
}
},
"required": [
"ip",
"categories"
],
"additionalProperties": false
}🟢get_blocklist(confidenceMinimum, exceptCountries, ipVersion, limit, onlyCountries)
The highest-confidence abusive addresses right now, best first, with score, country and categories. Needs an API key and counts as one blocklist download. For a firewall-ready file, point the firewall at the blocklist URL instead (see the integrations).
Input Schema
{
"type": "object",
"properties": {
"confidenceMinimum": {
"default": 75,
"description": "Lowest score to include",
"maximum": 100,
"minimum": 1,
"type": "integer"
},
"exceptCountries": {
"description": "Comma-separated ISO country codes to leave out",
"type": "string"
},
"ipVersion": {
"description": "Only IPv4 or only IPv6",
"enum": [
4,
6
],
"type": "integer"
},
"limit": {
"default": 100,
"description": "Maximum number of addresses",
"maximum": 1000,
"minimum": 1,
"type": "integer"
},
"onlyCountries": {
"description": "Comma-separated ISO country codes to include, e.g. CN,RU",
"type": "string"
}
},
"additionalProperties": false
}🟢list_categories
All attack categories with their code, numeric ID, group and when to use them. Use the codes with report_ip.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢get_statistics
What the database sees right now: reports in the last 24 hours, addresses on the blocklist, and over the last 30 days the top attack categories, countries, networks and highest-scoring addresses.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢get_today_news
Today's threat news from the last 24 hours: the countries the most reported attacks come from, the networks (ASNs) behind them, the attack techniques (categories) reported most, and the top 10 malicious IP addresses reported today, highest score first. Use it for a daily briefing on what is attacking right now.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢analyze_logs(logs)
Find malicious traffic in logs. Pass raw log lines from any source (nginx/Apache/IIS access logs, sshd/auth.log, syslog, firewall such as iptables/UFW/pfSense/ASA, mail servers, Windows events as text, CEF, JSON lines from a SIEM or cloud, CSV); every IPv4/IPv6 address is extracted wherever it appears and each non-blank line is one event. Returns how many events came from malicious (score 75+), suspicious (25-74) and unreported addresses, the top offenders with score and attack categories, the busiest addresses, countries, networks, attack categories, detected log formats, HTTP status classes, failed logins and the time range. Each distinct address looked up counts as one lookup against the daily allowance, busiest first. Per analysis: without a key 256 KB and 100 addresses, free key 2 MB and 1,000, Enterprise 5 MB and 10,000. The log is not stored. Remove secrets (passwords, tokens) before sending.
Input Schema
{
"type": "object",
"properties": {
"logs": {
"description": "The raw log text, one event per line, in any format",
"type": "string"
}
},
"required": [
"logs"
],
"additionalProperties": false
}🟢get_country_report(country)
How many addresses in a country were reported in the last 30 days, how many are on the blocklist, the most reported addresses there, and the networks and attack categories behind them.
Input Schema
{
"type": "object",
"properties": {
"country": {
"description": "ISO 3166-1 alpha-2 code, e.g. DE",
"type": "string"
}
},
"required": [
"country"
],
"additionalProperties": false
}🟢get_network_report(asn)
Abuse reported against one autonomous system in the last 30 days: number of reported and blocklisted addresses, the worst addresses, attack categories and countries. Useful to judge a hosting provider or ISP.
Input Schema
{
"type": "object",
"properties": {
"asn": {
"description": "AS number, with or without the AS prefix, e.g. AS14061 or 14061",
"type": "string"
}
},
"required": [
"asn"
],
"additionalProperties": false
}🟢about_isipsafe(topic)
Explains isIPsafe itself. Use it for any question about the product rather than guessing: what it is and who it is for, its mission and aims, how reports and the confidence score work, plans, pricing and limits, how to get started, how to get an address delisted, privacy, and who runs it. Needs no API key and uses no allowance.
Input Schema
{
"type": "object",
"properties": {
"topic": {
"default": "overview",
"description": "What to read about. overview: What the product is, who it is for and what it offers. Start here. mission: Why it exists, what it aims for, its principles and where it is heading. how_it_works: How reports become a confidence score, what the score means, and where the data comes from. plans: What is free, the limits of each plan, Enterprise, and what the data may be used for. getting_started: How to look addresses up, report attacks, use the blocklist, the API, the integrations and MCP. delisting: What to do about an address that is listed, whether by mistake or for good reason. privacy: What is stored about reporters and visitors, public profiles, GDPR and deleting an account. company: The team, the company behind the service, contact details and legal documents. faq: Every question on the FAQ page: basics, reporting, scores, the blocklist and API, delisting and privacy.",
"enum": [
"overview",
"mission",
"how_it_works",
"plans",
"getting_started",
"delisting",
"privacy",
"company",
"faq"
],
"type": "string"
}
},
"additionalProperties": false
}Community
Evidence