检索记忆或浮现未解决记忆。query 为空时自动推送权重最高的未解决桶；有 query 时按关键词+情感检索。domain 逗号分隔，valence/arousal 传 0~1 启用情感共鸣，-1 忽略。
AI agents call breath 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.
The 'breath' tool is fundamentally a retrieval/query mechanism for an emotional memory system. It searches, filters, and surfaces stored memories based on keywords and emotional parameters. It has no side effects that modify, delete, or execute operations. The tool is designed for read-only access to persistent memory records, making it a Read category classification.
From the tool's definition Tool retrieves or queries emotional memory records. Description indicates retrieval functionality: 'retrieves memory or surfaces unresolved memory' (检索记忆或浮现未解决记忆), 'query by keyword + emotion' (按关键词+情感检索), and 'auto-push highest weighted unresolved buckets'…
Documented attack patterns abuse exactly the kind of access breath 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 breath:
{
"version": "1",
"default": "deny",
"tools": {
"breath": {}
}
}breath 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.
检索记忆或浮现未解决记忆。query 为空时自动推送权重最高的未解决桶；有 query 时按关键词+情感检索。domain 逗号分隔，valence/arousal 传 0~1 启用情感共鸣，-1 忽略。. 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 breath: 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.
breath 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 breath 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 breath. 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.
breath 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.