Multi-algorithm native graph pathfinder (ADR-130 Phase 5). Use when agentdb_graph-query k-hop is not enough — pathfinder supports personalized-pagerank, dynamic-mincut, spectral-sparsify, temporal-centrality, connected-component-churn, and witness-chain-divergence. Prefer over prompt-level graph ...
AI agents call agentdb_graph-pathfinder 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 performs graph analysis and pathfinding — querying graph structures to find and rank paths using various algorithms. There is no indication of data modification, deletion, code execution, or financial operations. It is a sophisticated read/query tool.
From the tool's definition 'Multi-algorithm native graph pathfinder' and algorithms listed (personalized-pagerank, dynamic-mincut, spectral-sparsify, temporal-centrality, connected-component-churn, witness-chain-divergence) are all analytical/query operations; 'ranked paths with formal…
Attacks that exploit this kind of access
Multi-algorithm native graph pathfinder (ADR-130 Phase 5). Use when agentdb_graph-query k-hop is not enough — pathfinder supports personalized-pagerank, dynamic-mincut, spectral-sparsify, temporal-centrality, connected-component-churn, and witness-chain-divergence. Prefer over prompt-level graph loops in ruflo-knowledge-graph graph-navigator when you need ranked paths with formal complexityBudget enforcement. 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_graph-pathfinder: 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_graph-pathfinder 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_graph-pathfinder 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_graph-pathfinder. 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_graph-pathfinder 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.