Authoritative MITRE ATT&CK (Enterprise) technique lookup. Pass id (T1059 / T1059.001) for name, tactics, description, platforms, sub-technique parent, mitigations, detection — or query for keyword search. Bundled (~700 techniques), zero external calls. Agents cite T-numbers + tactics that must be...
AI agents call security.attack 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 data lookup service. It retrieves and returns information about known attack techniques from a bundled, static MITRE ATT&CK database. The tool supports threat modeling and detection engineering use cases via query and retrieval only. Even if an agent misuses it (e.g., to research attack vectors), the tool itself does not execute, create, modify, or destroy anything—it only returns information.
From the tool's definition Tool provides 'lookup' and 'keyword search' of MITRE ATT&CK technique data. Description emphasizes retrieval ('Pass id...for name, tactics, description') and states 'Bundled (~700 techniques), zero external calls.' No modification, deletion, code execution,…
Attacks that exploit this kind of access
Authoritative MITRE ATT&CK (Enterprise) technique lookup. Pass id (T1059 / T1059.001) for name, tactics, description, platforms, sub-technique parent, mitigations, detection — or query for keyword search. Bundled (~700 techniques), zero external calls. Agents cite T-numbers + tactics that must be exact. For threat modeling, detection engineering, report enrichment. 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.attack: 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.attack 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.attack 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.attack. 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.attack 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 →