Authoritative MITRE CAPEC (Common Attack Pattern Enumeration) lookup. Pass id (CAPEC-66 or 66) for name, abstraction, description, likelihood, severity, mapped CWE weaknesses + related patterns (with names) — or query for keyword search. Bundled (~615), zero external calls. The attacker view; CAP...
AI agents call security.capec 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 reference data retrieval tool that provides read-only access to MITRE CAPEC attack pattern information. It returns structured security knowledge for lookups and searches without side effects, state changes, or external operations. The fact that it's served on a financial payment infrastructure (2s.io USDC settlement) is immaterial to the tool's function—it's purely informational.
From the tool's definition Tool performs 'lookup' and 'keyword search' with 'zero external calls' and 'bundled' data; returns informational results (name, abstraction, description, likelihood, severity, mapped weaknesses, related patterns) without modifying, executing, or deleting…
Attacks that exploit this kind of access
Authoritative MITRE CAPEC (Common Attack Pattern Enumeration) lookup. Pass id (CAPEC-66 or 66) for name, abstraction, description, likelihood, severity, mapped CWE weaknesses + related patterns (with names) — or query for keyword search. Bundled (~615), zero external calls. The attacker view; CAPEC↔CWE cross-links let an agent pivot between an attack and the weakness it exploits. 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.capec: 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.capec 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.capec 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.capec. 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.capec 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 →