Get an entity edge from the graph memory by its UUID.
AI agents call get_entity_edge to retrieve information from local-RAG-backend without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a single entity edge from the Neo4j-backed graph using its UUID as a lookup parameter. There are no side effects, no data is created, modified, or deleted. This is a straightforward read operation on existing graph data, consistent with other retrieval tools in the sibling set like 'get_episodes' and 'get_status'.
From the tool's definition Tool name is 'get_entity_edge' and description states 'Get an entity edge from the graph memory by its UUID' — the verb 'Get' indicates data retrieval with no modification.
Attacks that exploit this kind of access
Get an entity edge from the graph memory by its UUID. It is categorised as a Read tool in the local-RAG-backend MCP Server, which means it retrieves data without modifying state.
Register the local-RAG-backend MCP server in PolicyLayer and add a rule for get_entity_edge: 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 local-RAG-backend. Nothing to install.
get_entity_edge 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 get_entity_edge 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 get_entity_edge. 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.
get_entity_edge is provided by the local-RAG-backend MCP server (suwa-sh/local-rag-backend). 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 →