Get or manage neural patterns Use when nothing native trains on your workflow — Claude Code has no learning loop. Use to train SONA/MoE/EWC patterns from successful task outcomes; query via neural_predict before spawning agents. Off-path for one-shot work.
AI agents use neural_patterns to create or update resources in Claude Flow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Flow environment.
This tool performs reversible Write operations: it trains (creates/updates) neural network patterns based on task outcomes and can be queried. While it modifies AI/ML model state, the effects are not irreversible deletions and do not constitute code execution or financial impact. The 'manage' capability could potentially include deletion, but the description emphasizes training and querying.
From the tool's definition Description states 'Get or manage neural patterns' and 'train SONA/MoE/EWC patterns from successful task outcomes' — the 'manage' and 'train' verbs indicate creation and modification of machine learning model state.
Attacks that exploit this kind of access
Get or manage neural patterns Use when nothing native trains on your workflow — Claude Code has no learning loop. Use to train SONA/MoE/EWC patterns from successful task outcomes; query via neural_predict before spawning agents. Off-path for one-shot work. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Flow MCP server in PolicyLayer and add a rule for neural_patterns: 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 Claude Flow. Nothing to install.
neural_patterns 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 neural_patterns 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 neural_patterns. 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.
neural_patterns is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.