Store learned pattern
AI agents use pattern_store 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.
Storing a learned pattern is a reversible write operation — it creates or updates a record in some pattern database or neural network store. There is no indication of deletion, code execution, or financial impact. Severity is medium because in an AI orchestration context, persisting incorrect or malicious patterns could influence downstream agent behavior at scale, but the action itself is a standard write.
From the tool's definition Tool name 'pattern_store' and description 'Store learned pattern' indicate a write/create operation persisting data to storage.
Attacks that exploit this kind of access
Store learned pattern. 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 pattern_store: 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.
pattern_store 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 pattern_store 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 pattern_store. 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.
pattern_store 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.