Opens a CueCrux session and returns a typed capability plan (retrieval, proofing, memory, journaling, audit) across VaultCrux and MemoryCrux. Call this first, once. Every subsequent action routes through the channels the plan returns — do not browse the legacy per-service tool list when a plan ch...
Risk signalsHigh parameter count (10 properties) · Bulk/mass operation — affects multiple targets
Part of the VaultCrux Memory Core server.
Free to start. No card required.
AI agents call cuecrux_session to retrieve information from VaultCrux Memory Core without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though cuecrux_session only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"cuecrux_session": {}
}
}See the full VaultCrux Memory Core policy for all 76 tools.
These attack patterns abuse exactly the kind of access cuecrux_session gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Opens a CueCrux session and returns a typed capability plan (retrieval, proofing, memory, journaling, audit) across VaultCrux and MemoryCrux. Call this first, once. Every subsequent action routes through the channels the plan returns — do not browse the legacy per-service tool list when a plan channel already covers the capability. Identical behaviour for local Crux CE and hosted CueCrux. Hosted deployments stage v1 flat-list or v2 typed-graph plan shapes behind feature flags; callers treat the returned plan as the single source of routing truth. Bulk-capable agents transparently use the HTTP/2 binary channel; MCP-only agents use the MCP fallback URLs the plan provides. Implements RCX-Protocol v1.0.. It is categorised as a Read tool in the VaultCrux Memory Core MCP Server, which means it retrieves data without modifying state.
Register the VaultCrux Memory Core MCP server in PolicyLayer and add a rule for cuecrux_session: 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 VaultCrux Memory Core. Nothing to install.
cuecrux_session 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 cuecrux_session 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 cuecrux_session. 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.
cuecrux_session is provided by the VaultCrux Memory Core MCP server (https://api.vaultcrux.com/platform/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 76 VaultCrux Memory Core tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.