Start a session with ReflexionMemory episodic replay 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/memo...
AI agents use agentdb_session-start 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.
Starting a session creates new state/records in the AgentDB system (episodic memory, session context). This is a Write operation as it initializes persistent data structures. It is not purely Read (it creates session state), not Destructive (sessions can be ended/cleaned up), and not Execute (no arbitrary code or commands are run).
From the tool's definition 'Start a session with ReflexionMemory episodic replay' — initiates and creates a new session state within AgentDB; also references 'pattern store/recall' and 'causal-graph links' implying data creation and modification
Attacks that exploit this kind of access
Start a session with ReflexionMemory episodic replay 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_session-start: 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_session-start 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_session-start 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_session-start. 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_session-start 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.