AI agents call check_mitre to retrieve information from SIFTGuard without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs threat intelligence correlation and classification by comparing observed artifacts against the MITRE ATT&CK framework. It reads/queries forensic findings and returns enriched threat categorization. This is fundamentally a read operation with no side effects on the evidence, system, or any external resources.
From the tool's definition Tool maps observed behavior to MITRE ATT&CK techniques—a classification and lookup operation against a static knowledge base. No modification of evidence, deletion, code execution, or financial transaction occurs.
Attacks that exploit this kind of access
Map observed attacker behavior to MITRE ATT&CK techniques and tactics. It is categorised as a Read tool in the SIFTGuard MCP Server, which means it retrieves data without modifying state.
Register the SIFTGuard MCP server in PolicyLayer and add a rule for check_mitre: 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 SIFTGuard. Nothing to install.
check_mitre 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 check_mitre 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 check_mitre. 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.
check_mitre is provided by the SIFTGuard MCP server (sodiq-code/siftguard). 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 →