Skip to main content
Glama

An MCP server that exposes AbuseIPDB threat intelligence as tools — ask Claude (or any MCP client) whether an IP, subnet, or set of reports looks malicious, and get real data back instead of a guess.

Tools

Tool

What it does

check_ip

Check a single IP — abuse confidence score, ISP, country, usage type, report count, optionally the last 10 individual reports

check_block

Check a CIDR network block (up to /16) — network range info plus a per-IP breakdown of any reported addresses inside it

get_reports

Get the individual abuse reports filed against an IP — who reported it, why, and when, paginated

get_blacklist

Get the most-reported IPs overall. Free tier is capped at confidence 100 regardless of what you ask for; paid tiers can widen the range

Related MCP server: FastMCP ThreatIntel

Prerequisites

  • Node.js 18+

  • A free AbuseIPDB API key (free tier: 1,000 checks/day, 5 blacklist calls/day)

Installation

Quick install

The package is published on npm, so these register it in one step — no cloning or building required:

Claude Code:

claude mcp add abuseipdb -e ABUSEIPDB_API_KEY=your-api-key-here -- npx -y mcp-abuseipdb

Codex CLI:

codex mcp add abuseipdb --env ABUSEIPDB_API_KEY=your-api-key-here -- npx -y mcp-abuseipdb

Manual config (any stdio MCP client)

Most clients that support stdio MCP servers (Claude Desktop, Cursor, Windsurf, etc.) use this same config shape — add it to whichever config file your client expects:

{
  "mcpServers": {
    "abuseipdb": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-abuseipdb/dist/index.js"],
      "env": {
        "ABUSEIPDB_API_KEY": "your-api-key-here"
      }
    }
  }
}

Restart your client, then try asking:

"Has 8.8.8.8 been reported for anything?"

"Check my office subnet 203.0.113.0/24 for abuse reports"

"What are the most reported IPs right now?"

How it works

MCP client (Claude, Inspector, ...)
        │  stdio, JSON-RPC
        ▼
  McpServer (src/server.ts)
        │
        ▼
  tools/*.ts     — one file per tool: Zod schema + handler, formats the reply
        │
        ▼
  endpoints/*.ts — one file per AbuseIPDB endpoint: typed request + response
        │
        ▼
  abuseipdbClient.ts — auth header, response envelope, AbuseIPDB error parsing
        │
        ▼
  client.ts      — generic fetch wrapper, timeout, HTTP error handling
        │
        ▼
  AbuseIPDB REST API

Each layer knows nothing about the one above it. client.ts doesn't know AbuseIPDB exists; endpoints/ doesn't know MCP exists. Adding a new tool means one new file in endpoints/, one new file in tools/, one line in tools/index.ts — nothing else changes.

Tool arguments are validated with Zod before any handler runs — a malformed request never reaches the API.

Development

git clone https://github.com/arminasbek/mcp-abuseipdb.git
cd mcp-abuseipdb
npm install
npm run build   # compile TypeScript
npm run lint     # check formatting + lint rules
npm run check    # lint + format + fix, in place

Test locally with the MCP Inspector:

npx @modelcontextprotocol/inspector --cli node --env-file=.env dist/index.js --method tools/call --tool-name check_ip --tool-arg ip=8.8.8.8

License

MIT

Available Tools

4 tools
check_blockA

Check a CIDR network block (e.g. a /24 subnet) for reported IPs — returns network range info plus a per-IP breakdown of any reported addresses within it. Use check_ip instead for a single IP address.

Inputs: network (required), max_age_in_days.

check_ipB

Check if an IP address has been reported for abusive behavior. Returns abuse confidence score (0-100), ISP, country, usage type, and report count.

Inputs: ip (required), verbose, max_age_in_days.

get_blacklistA

Get the most reported IP addresses. Free tier only returns confidence 100 results regardless of confidence_minimum; paid tiers can widen the range.

Inputs: limit, confidence_minimum.

get_reportsA

Get the individual abuse reports filed against an IP address — who reported it, why, and when.

Inputs: ip (required), page, per_page, max_age_in_days.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool targets a distinct abuse-related lookup: single IP, CIDR block, detailed reports, and top offenders. There is no overlap in purpose; even check_ip and get_reports complement rather than duplicate, since one gives a confidence score and the other gives specific incident details.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with imperative verbs: get_reports, check_ip, get_blacklist, check_block. The two verbs (get/check) are used predictably based on whether the action retrieves a list or evaluates a specific target.

    Tool Count5/5

    Four tools is well-scoped for an IP abuse lookup service, covering the core operations an agent would need: single IP check, network block check, report details, and blacklist retrieval. Each tool earns its place without redundancy or bloat.

    Completeness5/5

    The tool surface fully covers the read-only domain of IP abuse checking. There are no obvious missing operations for the stated purpose; the four tools provide both summary and detailed views across individual IPs and network ranges.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Integrates with the AbuseIPDB API to check IP addresses for abuse reports and report abusive IP addresses.
      2
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI-powered threat intelligence analysis of IPs, domains, URLs, and file hashes across multiple threat intelligence platforms (VirusTotal, AlienVault OTX, AbuseIPDB, IPinfo) with APT attribution and interactive reporting through natural language queries.
      28 PyPI
      40
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      Provides threat intelligence lookups against the AbuseIPDB database, enabling IP reputation checks, CIDR block analysis, and log enrichment. It features intelligent caching and rate limiting to efficiently manage API usage for security analysis and automated workflows.
      5
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to check IP reputation and abuse reports via AbuseIPDB, including abuse confidence scores, report details, and bulk IP triage.
      8 npm
      1
      MIT