search_entities
AI agents call search_entities to retrieve information from Neo4j Knowledge Graph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to search or query entities within the Neo4j knowledge graph. Despite the empty description, the name and server context (which lists search as a read operation alongside create, update, and delete) indicate this is a retrieval operation with no side effects.
From the tool's definition Tool name 'search_entities' and server description context indicating 'search...entities' as a retrieval operation without modification. Description is empty, which lowers confidence slightly.
Attacks that exploit this kind of access
search_entities. It is categorised as a Read tool in the Neo4j Knowledge Graph MCP Server, which means it retrieves data without modifying state.
Register the Neo4j Knowledge Graph MCP server in PolicyLayer and add a rule for search_entities: 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 Neo4j Knowledge Graph. Nothing to install.
search_entities 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 search_entities 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 search_entities. 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.
search_entities is provided by the Neo4j Knowledge Graph MCP server (mjftw/mcp_neo4j_knowledge_graph). 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 →