Multi-hop graph traversal starting from a node URI. Follows all links where the node appears as source or target, expanding outward to the given depth (default 2, max 4). Returns the full connected subgraph — nodes, edges, and edges grouped by predicate — so Claude can reason over connected facts...
AI agents call ad4m_traverse to retrieve information from Mcp Ad4m without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
ad4m_traverse retrieves and queries semantic graph data starting from a node URI and expanding to connected nodes up to a specified depth. It has no side effects—it does not create, modify, delete, or execute operations. The tool is purely informational, allowing Claude to reason over existing connected facts in the semantic memory. This is a classic Read operation.
From the tool's definition Tool description states it 'Follows all links' and 'Returns the full connected subgraph — nodes, edges, and edges grouped by predicate' with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Multi-hop graph traversal starting from a node URI. Follows all links where the node appears as source or target, expanding outward to the given depth (default 2, max 4). Returns the full connected subgraph — nodes, edges, and edges grouped by predicate — so Claude can reason over connected facts without requiring formal logic. It is categorised as a Read tool in the Mcp Ad4m MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ad4m MCP server in PolicyLayer and add a rule for ad4m_traverse: 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 Mcp Ad4m. Nothing to install.
ad4m_traverse 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 ad4m_traverse 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 ad4m_traverse. 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.
ad4m_traverse is provided by the Mcp Ad4m MCP server (thefranceway/mcp-ad4m). 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 →