AI agents call get_node_properties_keys to retrieve information from Neo4j Gds without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to query and retrieve node property keys from the Neo4j graph database. This is a read operation with no side effects—it extracts metadata about available properties on nodes but does not create, modify, delete, or execute arbitrary code. Even with an empty description, the naming convention strongly suggests introspection/metadata retrieval.
From the tool's definition Tool name 'get_node_properties_keys' indicates retrieval of property key metadata from graph nodes. The description is empty, but the function name suggests a read-only query operation that retrieves schema or structural information without modifying data.
Attacks that exploit this kind of access
get_node_properties_keys. It is categorised as a Read tool in the Neo4j Gds MCP Server, which means it retrieves data without modifying state.
Register the Neo4j Gds MCP server in PolicyLayer and add a rule for get_node_properties_keys: 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 Gds. Nothing to install.
get_node_properties_keys 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_node_properties_keys 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_node_properties_keys. 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_node_properties_keys is provided by the Neo4j Gds MCP server (neo4j-contrib/gds-agent). 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 →