AI agents call main to retrieve information from Ombre Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without explicit description, classification relies on context from the memory system's stated purpose and naming patterns of sibling tools. The tool appears to be a primary accessor for retrieving emotional memory data. Confidence is moderate due to empty description; if it actually performs state modifications or deletions, the category could shift to Write or Destructive.
From the tool's definition Tool name is 'main' with no description provided. Based on sibling tools (breath, grow, hold, pulse, trace) which suggest memory querying/retrieval operations, 'main' likely retrieves or accesses emotional memory state rather than modifying it.
Documented attack patterns abuse exactly the kind of access main gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ombre Brain, and nothing reaches the server without passing your rules. This is the rule we recommend for main:
{
"version": "1",
"default": "deny",
"tools": {
"main": {}
}
}main 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.
main. It is categorised as a Read tool in the Ombre Brain MCP Server, which means it retrieves data without modifying state.
Register the Ombre Brain MCP server in PolicyLayer and add a rule for main: 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 Ombre Brain. Nothing to install.
main 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 main 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 main. 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.
main is provided by the Ombre Brain MCP server (p0lar1zzz/ombre-brain). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Ombre Brain tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Ombre Brain tools catalogued and risk-classified — across an index of 42,500+ MCP servers.