Get all edges (relationships) from the user knowledge graph
AI agents call zep_get_graph_edges to retrieve information from Zep 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 existing graph relationship data without creating, modifying, deleting, or executing any operations. It has no side effects and falls squarely into the Read category for data retrieval operations.
From the tool's definition Tool name 'zep_get_graph_edges' uses the verb 'Get', and description states 'Get all edges (relationships)' indicating data retrieval with no modification. This is a read-only operation that retrieves relationship data from an existing knowledge graph.
Attacks that exploit this kind of access
Get all edges (relationships) from the user knowledge graph. It is categorised as a Read tool in the Zep MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Zep MCP Server MCP server in PolicyLayer and add a rule for zep_get_graph_edges: 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 Zep MCP Server. Nothing to install.
zep_get_graph_edges 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 zep_get_graph_edges 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 zep_get_graph_edges. 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.
zep_get_graph_edges is provided by the Zep MCP Server MCP server (wastrilith2k/zep-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 →