Get AgentDB v3 controller health status including cache stats and attestation count 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...
AI agents call agentdb_health 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.
The tool only reads and returns health/status information (cache stats, attestation count) from the AgentDB controller. This is a diagnostic/monitoring read operation with no data modification, execution, or destructive capabilities. Misuse potential is minimal as it only exposes system health metadata.
From the tool's definition 'Get AgentDB v3 controller health status including cache stats and attestation count' — purely retrieves status/health information with no side effects mentioned
Attacks that exploit this kind of access
Get AgentDB v3 controller health status including cache stats and attestation count 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_health: 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_health 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_health 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_health. 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_health 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.