Cascade-delete a causal node and all its incident edges from the SQL fallback. Native graph-node entries are unaffected (no delete API in the binding). Use when generic memory_* tools are wrong because you need AgentDB-specific controllers (HNSW vector search, hierarchical tiers, causal-graph lin...
AI agents call agentdb_causal-node-delete to permanently remove resources in Claude Flow — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs irreversible deletion of database records (causal nodes and edges) with cascade semantics, affecting dependent data. The cascade behavior amplifies the destructive impact beyond the directly targeted node. While the description notes that native graph-node entries are unaffected, the explicit cascade-delete operation on SQL-backed persistence makes this clearly Destructive rather than Write.
From the tool's definition Tool name contains 'delete'; description states 'Cascade-delete a causal node and all its incident edges from the SQL fallback' — irreversible deletion of data structures and their dependencies.
Attacks that exploit this kind of access
Cascade-delete a causal node and all its incident edges from the SQL fallback. Native graph-node entries are unaffected (no delete API in the binding). 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 Destructive tool in the Claude Flow MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Flow MCP server in PolicyLayer and add a rule for agentdb_causal-node-delete: 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_causal-node-delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the agentdb_causal-node-delete 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_causal-node-delete. 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_causal-node-delete 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.