Decision archaeology across Memory Crystal decision memories.
AI agents call crystal_why_did_we to retrieve information from Memory Crystal MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes historical decision data from the Memory Crystal system. It performs lookback analysis ('archaeology') on existing memory records to understand reasoning behind past decisions. This is a Read operation—it queries stored information without side effects, does not modify data, execute code, delete anything, or commit financial transactions.
From the tool's definition The tool name 'crystal_why_did_we' and description 'Decision archaeology across Memory Crystal decision memories' indicate a query or retrieval operation.
Documented attack patterns abuse exactly the kind of access crystal_why_did_we gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memory Crystal MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for crystal_why_did_we:
{
"version": "1",
"default": "deny",
"tools": {
"crystal_why_did_we": {}
}
} crystal_why_did_we 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.
Decision archaeology across Memory Crystal decision memories. It is categorised as a Read tool in the Memory Crystal MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Memory Crystal MCP Server MCP server in PolicyLayer and add a rule for crystal_why_did_we: 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 Memory Crystal MCP Server. Nothing to install.
crystal_why_did_we 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 crystal_why_did_we 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 crystal_why_did_we. 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.
crystal_why_did_we is provided by the Memory Crystal MCP Server MCP server (memorycrystal/memorycrystal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memory Crystal MCP Server, 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.
31 Memory Crystal MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.