AI agents call find_neighbors to retrieve information from NebulaGraph MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only graph traversal to retrieve neighboring vertices. It retrieves or queries data (the neighbors of a vertex) with no side effects, reversible modifications, code execution, destructive operations, or financial impact. It falls squarely into the Read category as a data retrieval operation.
From the tool's definition Tool name 'find_neighbors' and description 'Find the neighbors of the specified vertex' indicate a query operation that retrieves data about graph connections without modifying or deleting any data.
Documented attack patterns abuse exactly the kind of access find_neighbors gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and NebulaGraph MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for find_neighbors:
{
"version": "1",
"default": "deny",
"tools": {
"find_neighbors": {}
}
} find_neighbors is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find the neighbors of the specified vertex. It is categorised as a Read tool in the NebulaGraph MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NebulaGraph MCP Server MCP server in PolicyLayer and add a rule for find_neighbors: 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 NebulaGraph MCP Server. Nothing to install.
find_neighbors 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 find_neighbors 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 find_neighbors. 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.
find_neighbors is provided by the NebulaGraph MCP Server MCP server (nebula-contrib/nebulagraph-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from NebulaGraph MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 NebulaGraph MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.