Unified graph traversal across the knowledge graph (ADR-130). Dispatches to the most capable backend: graph-node native for k-hop, sql.js CTE for fallback, HNSW cosine for semantic, ruflo-graph-intelligence PageRank for pagerank mode. Use when you need structured graph traversal beyond flat memor...
AI agents call agentdb_graph-query 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.
This tool performs traversal and querying of a knowledge graph across multiple backend engines. The description emphasizes retrieval ('traversal', 'search') with no mention of create, modify, delete, or execute capabilities.
From the tool's definition Tool is described as 'Unified graph traversal' and 'graph traversal' which retrieves structured data from a knowledge graph. Dispatches to backends for querying (k-hop, CTE, semantic, PageRank) without modification capabilities mentioned.
Attacks that exploit this kind of access
Unified graph traversal across the knowledge graph (ADR-130). Dispatches to the most capable backend: graph-node native for k-hop, sql.js CTE for fallback, HNSW cosine for semantic, ruflo-graph-intelligence PageRank for pagerank mode. Use when you need structured graph traversal beyond flat memory search. 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-query: 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-query 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-query 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-query. 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-query 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.