What's always true — automatic findings and on-demand checks. Automatic outputs: conservationLaws (weighted entity sums constant across executions), sustainableCycles (T-invariants — action sequences returning to start state), depletableSets (entity groups whose simultaneous depletion is irrevers...
Part of the Endiagram server.
Free to start. No card required.
AI agents may call invariant to permanently remove or destroy resources in Endiagram. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call invariant in a loop, permanently destroying resources in Endiagram. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"invariant"
]
}See the full Endiagram policy for all 7 tools.
These attack patterns abuse exactly the kind of access invariant gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
What's always true — automatic findings and on-demand checks. Automatic outputs: conservationLaws (weighted entity sums constant across executions), sustainableCycles (T-invariants — action sequences returning to start state), depletableSets (entity groups whose simultaneous depletion is irreversible), behavioral.deficiency (0 means structure fully determines dynamics), behavioral.isReversible, behavioral.hasUniqueEquilibrium. On-demand via rules: encode domain-specific claims and verify them against the graph — this is how to check things the topology alone can't see (precedence, coverage, centrality bounds, resilience). See the rules parameter for supported sentence shapes.. It is categorised as a Destructive tool in the Endiagram MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Endiagram MCP server in PolicyLayer and add a rule for invariant: 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 Endiagram. Nothing to install.
invariant is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the invariant 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 invariant. 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.
invariant is provided by the Endiagram MCP server (@endiagram/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Endiagram 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.