Get mitigations for a specific threat
AI agents call get_mitigations_by_threat to retrieve information from Devici MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves mitigations associated with a threat model. It performs a read-only operation with no side effects, data modification, code execution, or irreversible actions. The low blast radius reflects that an AI agent misusing this tool could only access threat mitigation information, not alter security posture or trigger external operations.
From the tool's definition Tool name contains 'get_' and description explicitly states 'Get mitigations for a specific threat' — a retrieval operation with no modification or execution.
Attacks that exploit this kind of access
Get mitigations for a specific threat. It is categorised as a Read tool in the Devici MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Devici MCP Server MCP server in PolicyLayer and add a rule for get_mitigations_by_threat: 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 Devici MCP Server. Nothing to install.
get_mitigations_by_threat 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 get_mitigations_by_threat 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 get_mitigations_by_threat. 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.
get_mitigations_by_threat is provided by the Devici MCP Server MCP server (sdelements/devici-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 →