agentdb_causal-edge
Record a causal edge between two memory entries via CausalMemoryGraph 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, ...
This record as markdown: /tools/io-github-ruvnet-claude-flow/agentdb-causal-edge.md
What agentdb_causal-edge does on Claude Flow
AI agents use agentdb_causal-edge 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.
Why agentdb_causal-edge is rated Medium
This tool creates or modifies relationships (edges) in a graph data structure representing causal memory links between two entries. While it doesn't delete data (hence not Destructive) and doesn't execute arbitrary code (hence not Execute), it does persistently modify structured data by adding or updating causal relationships.
From the tool's definition Tool description states 'Record a causal edge' and explicitly mentions creating links in a CausalMemoryGraph. The verb 'record' combined with graph-manipulation context indicates data creation/modification rather than retrieval or deletion.
Attacks that exploit this kind of access
The rule that runs agentdb_causal-edge safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For agentdb_causal-edge, this is the rule to start with:
agentdb_causal-edge stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every agentdb_causal-edge call is checked against it from then on.
Questions about agentdb_causal-edge
Record a causal edge between two memory entries via CausalMemoryGraph 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_causal-edge: 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-edge 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_causal-edge 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-edge. 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-edge 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.
More on Claude Flow, and thousands of servers like it.
This server
Across the catalogue