Maps a VERITAS verdict to a CLAEG terminal state: PASS→STABLE_CONTINUATION, MODEL_BOUND/INCONCLUSIVE→ISOLATED_CONTAINMENT, VIOLATION→TERMINAL_SHUTDOWN.
AI agents use veritas_claeg_resolve to create or update resources in Mcp-Omega-Brain — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp-Omega-Brain environment.
An AI agent can call veritas_claeg_resolve faster than any human can review — one bad instruction and it creates or modifies resources in Mcp-Omega-Brain by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Maps a VERITAS verdict to a CLAEG terminal state: PASS→STABLE_CONTINUATION, MODEL_BOUND/INCONCLUSIVE→ISOLATED_CONTAINMENT, VIOLATION→TERMINAL_SHUTDOWN. It is categorised as a Write tool in the Mcp-Omega-Brain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp-Omega-Brain MCP server in PolicyLayer and add a rule for veritas_claeg_resolve: 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 Mcp-Omega-Brain. Nothing to install.
veritas_claeg_resolve is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the veritas_claeg_resolve 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 veritas_claeg_resolve. 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.
veritas_claeg_resolve is provided by the Mcp-Omega-Brain MCP server (vrtxomega/omega-brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.