Multi-source IP reputation with one combined authority score (0-100). Polls AbuseIPDB (crowd abuse confidence), abuse.ch threat-lists (Feodo C2 + ThreatFox + Spamhaus DROP + Tor), blocklist.de (fail2ban network), and StopForumSpam in parallel and blends them into a verdict (clean/low/suspicious/m...
AI agents call security.ip-reputation 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 tool purely retrieves and aggregates reputation data about an IP address from multiple sources. It performs read-only lookups with no side effects. The financial aspect (USDC pay-per-call) is a server-level billing mechanism, not a financial action performed by this specific tool. Severity is low because misuse would only expose threat intelligence data.
From the tool's definition Multi-source IP reputation... Polls AbuseIPDB... blends them into a verdict (clean/low/suspicious/malicious) + flaggedBy + per-source opinions + enrichment (ISP, usage type, country, ASN, Tor)
Attacks that exploit this kind of access
Multi-source IP reputation with one combined authority score (0-100). Polls AbuseIPDB (crowd abuse confidence), abuse.ch threat-lists (Feodo C2 + ThreatFox + Spamhaus DROP + Tor), blocklist.de (fail2ban network), and StopForumSpam in parallel and blends them into a verdict (clean/low/suspicious/malicious) + flaggedBy + per-source opinions + enrichment (ISP, usage type, country, ASN, Tor). Authoritative threat-list hits hard-floor the verdict at malicious. The one-call. 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-reputation: 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-reputation 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-reputation 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-reputation. 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-reputation 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 →