agentdb_pattern-store
Store a pattern directly via ReasoningBank controller Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern store/recall, RaBitQ quantization). For simple key-value persistence, memory_store/mem...
This record as markdown: /tools/io-github-ruvnet-claude-flow/agentdb-pattern-store.md
What agentdb_pattern-store does on Claude Flow
AI agents use agentdb_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.
Why agentdb_pattern-store is rated Medium
This tool writes data to a specialized pattern storage system rather than just retrieving it. While reversible (patterns can be updated or replaced), it modifies persistent state in an enterprise AI orchestration system.
From the tool's definition Tool description states 'Store a pattern directly' and explicitly mentions 'pattern store/recall', indicating it creates or modifies data in the AgentDB system.
Attacks that exploit this kind of access
The rule that runs agentdb_pattern-store safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For agentdb_pattern-store, this is the rule to start with:
agentdb_pattern-store stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every agentdb_pattern-store call is checked against it from then on.
Questions about agentdb_pattern-store
Store a pattern directly via ReasoningBank controller Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph links, pattern store/recall, RaBitQ quantization). For simple key-value persistence, memory_store/memory_retrieve are simpler. For unrelated file work, native Read/Write are fine. 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 agentdb_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.
agentdb_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 agentdb_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 agentdb_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.
agentdb_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.
More on Claude Flow, and thousands of servers like it.
This server
Across the catalogue