{
  "markdown": "# AbuseIPDB — IP Reputation and Threat Intelligence\n\nAbuseIPDB is a community-curated database of IPs reported for malicious activity (brute force, DDoS, web spam, credential stuffing, etc.). ~150M+ historical reports across millions of IPs. Each IP gets a confidence score (0-100) based on report volume, recency, and reporter trust. Used by sysadmins, security teams, and AI agents doing threat intelligence.\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Why this matters for AI agents\n\nFor security analysis — investigating a suspicious IP in logs, scoring inbound traffic, building blocklists — AbuseIPDB is the canonical free reputation source. Pair with [NVD](/docs/reference/nvd) for vulnerability research and [Shodan / PhishTank / URLhaus](/docs/reference) for adjacent threat intel.\n\nCommon flows:\n\n- **IP check.** \"What's the reputation of 1.2.3.4?\" → confidence score, recent reports, abuse categories.\n- **Blacklist pull.** \"Get a list of IPs flagged as DDoS sources in the last 90 days\" → filtered blacklist export.\n- **Report submission.** If you have evidence of abuse from an IP, you can submit a report (counts toward the reporter's trust score).\n\n## Auth\n\nAbuseIPDB requires a free API key from https://www.abuseipdb.com/account/api. Free tier: 1,000 requests/day. Pass via `_apiKey`.\n\n## Confidence score interpretation\n\n| Score | Meaning |\n|---|---|\n| 0 | Never reported (or fully whitelisted) |\n| 1-25 | Few reports, low confidence |\n| 26-75 | Moderate concern; multiple reports across time |\n| 76-100 | High confidence; active or recent malicious activity |\n\nFor automated blocking, 75+ is the conservative threshold. For alerting/triage, 25+ catches more activity.\n\n## Abuse categories\n\nEach report tags categories (multiple per report):\n\n| Category ID | Activity |\n|---|---|\n| 3 | Fraud Orders |\n| 4 | DDoS Attack |\n| 5 | FTP Brute-Force |\n| 9 | Open Proxy |\n| 10 | Web Spam |\n| 11 | Email Spam |\n| 14 | Port Scan |\n| 15 | Hacking |\n| 18 | Brute-Force |\n| 19 | Bad Web Bot |\n| 21 | Web App Attack |\n| 22 | SSH Brute-Force |\n\nFor agent-driven triage, category-aware filtering catches false positives (an IP flagged only as \"Web Spam\" is different from one flagged as \"Hacking\").\n\n## Common pitfalls\n\n- **Score is reporter-weighted.** A handful of trusted reporters carries more weight than many anonymous ones. Don't assume \"reported by 100 sources\" means 100 separate organizations — could be one researcher's 100 honeypots.\n- **NAT and shared IPs.** Carrier-grade NAT, AWS / GCP exit IPs, and Tor exit nodes get flagged constantly. A high score for a known shared IP doesn't necessarily implicate any single user.\n- **Historical decay.** Recent reports weight more than older ones. An IP that was malicious in 2019 but clean since may have a residual score that's no longer accurate.\n- **Self-reporting bias.** People report what they detect; sophisticated attacks (low-and-slow, residential proxies) underreport.\n- **False positives from scanning.** Legitimate vulnerability scanners (Shodan, Censys) get reported as abuse by uninformed sysadmins. Their IPs are well-known; whitelist them client-side.\n- **Rate limiting on free tier.** 1,000/day may not be enough for production — consider commercial tier or aggregate at the agent level via [memory](/docs/concepts/memory).\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"abuseipdb\": {\n      \"url\": \"https://gateway.pipeworx.io/abuseipdb/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/abuseipdb/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Abuseipdb data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 5404,
  "sha": "2d3dbe6815f884af135a55a87d4cfbf644090e8eaee51907970ec3546aa7c530",
  "repo_slug": "pipeworx-io/mcp-abuseipdb",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_abuseipdb_3cd23ba7/readme"
}