AbuseIPDB subnet (CIDR) check — which IPs inside a network block have been reported. Pass network as a CIDR (e.g. 118.25.0.0/24; up to /16 IPv4, /112 IPv6). Returns block metadata + reportedAddress (each flagged IP with numReports, confidence, mostRecentReport, country). Optional maxAgeInDays (de...
AI agents call security.ip-block 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.
The tool performs a lookup/query against AbuseIPDB to retrieve existing abuse report information about IP blocks. It has no capability to modify, delete, execute code, move funds, or trigger external operations. The worst misuse would be reconnaissance of network abuse history, which is low severity.
From the tool's definition Tool retrieves abuse report data about IP addresses using AbuseIPDB: 'returns block metadata + reportedAddress (each flagged IP with numReports, confidence, mostRecentReport, country)'. This is a query operation with no side effects.
Attacks that exploit this kind of access
AbuseIPDB subnet (CIDR) check — which IPs inside a network block have been reported. Pass network as a CIDR (e.g. 118.25.0.0/24; up to /16 IPv4, /112 IPv6). Returns block metadata + reportedAddress (each flagged IP with numReports, confidence, mostRecentReport, country). Optional maxAgeInDays (default 30), limit. Vet a hosting range or sweep your own allocation. 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-block: 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-block 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-block 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-block. 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-block 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 →