graph_traverse

Multi-hop graph traversal from an entity. Returns all paths with entities and relations at each hop. Supports direction and relation-type filtering.

Server Mementos @hasna/mementos
Category Read
Risk class Low
Parameters 00 required

What graph_traverse does on Mementos

AI agents call graph_traverse to retrieve information from Mementos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why graph_traverse needs a policy

This tool performs multi-hop traversal across a graph structure and returns results without creating, modifying, deleting, or executing external operations. It is purely informational/investigative in nature. The filtering parameters (direction, relation-type) are query constraints, not actions.

From the tool's definition Tool description states it 'Returns all paths with entities and relations' - a retrieval operation with no modification or side effects. Graph traversal is a query operation that reads existing data structure.

Questions about graph_traverse

What does the graph_traverse tool do? +

Multi-hop graph traversal from an entity. Returns all paths with entities and relations at each hop. Supports direction and relation-type filtering. It is categorised as a Read tool in the Mementos MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on graph_traverse? +

Register the Mementos MCP server in PolicyLayer and add a rule for graph_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 Mementos. Nothing to install.

What risk level is graph_traverse? +

graph_traverse is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit graph_traverse? +

Yes. Add a rate_limit block to the graph_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.

How do I block graph_traverse completely? +

Set action: deny in the PolicyLayer policy for graph_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.

What MCP server provides graph_traverse? +

graph_traverse is provided by the Mementos MCP server (@hasna/mementos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.