AbuseIPDB single-IP abuse check. Pass ip (IPv4/IPv6). Returns abuseConfidenceScore (0-100), totalReports, numDistinctUsers, lastReportedAt, usageType, ISP, domain, hostnames, isTor, isWhitelisted, country. verbose=true adds individual report records; maxAgeInDays (1-365, default 90) bounds the wi...
AI agents call security.ip-abuse to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query tool that retrieves existing abuse reputation data about IP addresses. While the information could inform security decisions (e.g., blocking or rate-limiting), the tool itself performs no write, execute, or financial operations. The severity is low because misuse would only surface stale or irrelevant reputation data, not cause direct harm.
From the tool's definition Tool queries AbuseIPDB for IP reputation data and returns abuse reports, confidence scores, and metadata (isTor, isWhitelisted, country, hostnames, etc.). No mutation, deletion, execution, or financial transaction occurs.
Attacks that exploit this kind of access
AbuseIPDB single-IP abuse check. Pass ip (IPv4/IPv6). Returns abuseConfidenceScore (0-100), totalReports, numDistinctUsers, lastReportedAt, usageType, ISP, domain, hostnames, isTor, isWhitelisted, country. verbose=true adds individual report records; maxAgeInDays (1-365, default 90) bounds the window. Live crowd data for SOC triage and login-abuse blocking. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for security.ip-abuse: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp. Nothing to install.
security.ip-abuse is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the security.ip-abuse rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for security.ip-abuse. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
security.ip-abuse is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →