agentdb_causal-edge-delete

Delete a causal edge between two memory entries. Returns controller=

Server Claude Flow claude-flow
Category Destructive
Risk class Critical
Parameters 00 required

What agentdb_causal-edge-delete does on Claude Flow

AI agents call agentdb_causal-edge-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.

Why agentdb_causal-edge-delete needs a policy

This tool irreversibly deletes data (a causal edge/relationship) from a database. Even though individual edges may seem small, in a hive-mind swarm orchestration system, causal edges represent critical reasoning pathways. Deleting these could break agent decision chains, corrupt multi-agent coordination logic, or undermine the integrity of shared memory.

From the tool's definition Tool name contains 'delete' and description states 'Delete a causal edge between two memory entries.' The action is irreversible deletion of a relationship/edge in what appears to be a knowledge graph or causal reasoning system.

Questions about agentdb_causal-edge-delete

What does the agentdb_causal-edge-delete tool do? +

Delete a causal edge between two memory entries. Returns controller=. 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.

How do I enforce a policy on agentdb_causal-edge-delete? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for agentdb_causal-edge-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.

What risk level is agentdb_causal-edge-delete? +

agentdb_causal-edge-delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit agentdb_causal-edge-delete? +

Yes. Add a rate_limit block to the agentdb_causal-edge-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.

How do I block agentdb_causal-edge-delete completely? +

Set action: deny in the PolicyLayer policy for agentdb_causal-edge-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.

What MCP server provides agentdb_causal-edge-delete? +

agentdb_causal-edge-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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.