Check if a decision aligns with your principles.
AI agents call alignment_check to retrieve information from Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a lookup or validation operation that reads stored principles and compares them against a decision. It produces informational output without altering state, creating obligations, or triggering external actions. The minimal blast radius if misused would be incorrect advice based on outdated principles, not resource damage or irreversible consequences.
From the tool's definition The tool name 'alignment_check' and description 'Check if a decision aligns with your principles' indicate it retrieves or queries information (checking/reading principles and decisions) with no side effects. No data is modified, deleted, or executed.
Documented attack patterns abuse exactly the kind of access alignment_check gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Brain, and nothing reaches the server without passing your rules. This is the rule we recommend for alignment_check:
{
"version": "1",
"default": "deny",
"tools": {
"alignment_check": {}
}
}alignment_check is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Check if a decision aligns with your principles. It is categorised as a Read tool in the Brain MCP Server, which means it retrieves data without modifying state.
Register the Brain MCP server in PolicyLayer and add a rule for alignment_check: 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 Brain. Nothing to install.
alignment_check 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 alignment_check 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 alignment_check. 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.
alignment_check is provided by the Brain MCP server (mordechaipotash/brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Brain, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
34 Brain tools catalogued and risk-classified — across an index of 43,000+ MCP servers.