Find all nodes connected to a given node within N hops using BFS.
AI agents call dual_ai_graph_connected to retrieve information from DUAL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries graph structure data without modifying, deleting, executing code, or performing financial transactions. It is a pure read operation similar to a graph database query. The low severity reflects minimal blast radius even if misused — returning graph connectivity data does not cause irreversible damage, unauthorized state changes, or financial impact.
From the tool's definition The tool 'dual_ai_graph_connected' performs a graph traversal query using breadth-first search (BFS) to find connected nodes.
Attacks that exploit this kind of access
Find all nodes connected to a given node within N hops using BFS. It is categorised as a Read tool in the DUAL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DUAL MCP Server MCP server in PolicyLayer and add a rule for dual_ai_graph_connected: 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 DUAL MCP Server. Nothing to install.
dual_ai_graph_connected 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 dual_ai_graph_connected 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 dual_ai_graph_connected. 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.
dual_ai_graph_connected is provided by the DUAL MCP Server MCP server (ro-ro-b/dual-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →