Search patterns via ReasoningBank controller with BM25+semantic hybrid 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,...
AI agents call agentdb_pattern-search to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from the AgentDB pattern store using hybrid search (BM25 and semantic similarity). Despite the complex infrastructure (HNSW, RaBitQ, causal graphs), the core function is data retrieval with no side effects, no code execution, and no data modification or deletion. The mention of 'store/recall' refers to the capability to find stored patterns, not to perform writes.
From the tool's definition 'Search patterns' describes a read-only query operation; the description emphasizes 'BM25+semantic hybrid' search and mentions 'vector search' and 'pattern store/recall' as retrieval mechanisms, not modification or deletion.
Attacks that exploit this kind of access
Search patterns via ReasoningBank controller with BM25+semantic hybrid 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 Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for agentdb_pattern-search: 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-search 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 agentdb_pattern-search 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-search. 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-search 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.