Authoritative MITRE CWE (Common Weakness Enumeration) lookup. Pass id (CWE-79 or 79) for the canonical weakness — name, abstraction, description, ChildOf/ParentOf relationships, mapped CAPEC patterns (all with names) — or query for keyword search. Bundled (~970), zero external calls. Anti-halluci...
AI agents call security.cwe 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 lookup tool that retrieves and searches MITRE CWE vulnerability information from a bundled local database ('Bundled (~970), zero external calls'). It has no side effects, cannot modify data, and merely provides informational read access to security weakness enumeration data. The mention of it being 'pay-per-call' relates to the server's billing model, not this tool's capabilities.
From the tool's definition Tool performs lookup and query operations: 'Pass id (CWE-79 or 79) for the canonical weakness — name, abstraction, description, ChildOf/ParentOf relationships, mapped CAPEC patterns' and 'query for keyword search'.
Attacks that exploit this kind of access
Authoritative MITRE CWE (Common Weakness Enumeration) lookup. Pass id (CWE-79 or 79) for the canonical weakness — name, abstraction, description, ChildOf/ParentOf relationships, mapped CAPEC patterns (all with names) — or query for keyword search. Bundled (~970), zero external calls. Anti-hallucination: agents cite CWE IDs/names that must be exact. Pairs with security.cve + security.capec. 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.cwe: 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.cwe 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.cwe 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.cwe. 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.cwe 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 →