Evaluates a specific existing item (by item_type and item_id) against all applicable governance rules. Use AFTER an item is logged to verify compliance, or as a pre-check during the governance gate. Returns conflict details: {has_conflict: bool, conflicts: [...], action:
AI agents call check_compliance to retrieve information from Engrams without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
check_compliance is a read-only query operation that retrieves and evaluates compliance information about an existing item. It has no capability to modify, delete, execute code, or trigger external operations. The worst outcome of misuse is unnecessary compliance checking or information disclosure, both low-severity.
From the tool's definition Tool evaluates and returns conflict details about existing items against governance rules. The description explicitly states it 'Returns conflict details' and is used 'to verify compliance' or as a 'pre-check'.
Documented attack patterns abuse exactly the kind of access check_compliance gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Engrams, and nothing reaches the server without passing your rules. This is the rule we recommend for check_compliance:
{
"version": "1",
"default": "deny",
"tools": {
"check_compliance": {}
}
}check_compliance 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.
Evaluates a specific existing item (by item_type and item_id) against all applicable governance rules. Use AFTER an item is logged to verify compliance, or as a pre-check during the governance gate. Returns conflict details: {has_conflict: bool, conflicts: [...], action:. It is categorised as a Read tool in the Engrams MCP Server, which means it retrieves data without modifying state.
Register the Engrams MCP server in PolicyLayer and add a rule for check_compliance: 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 Engrams. Nothing to install.
check_compliance 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_compliance 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_compliance. 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_compliance is provided by the Engrams MCP server (stevebrownlee/engrams). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Engrams, 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.
42 Engrams tools catalogued and risk-classified — across an index of 43,000+ MCP servers.