AI agents invoke find_path to trigger actions in NebulaGraph MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool runs a graph traversal/path algorithm on the database, which constitutes executing an operation against an external system. It reads data but does so via active query execution rather than a simple fetch. No data is modified or deleted, so it falls under Execute rather than Write or Destructive.
From the tool's definition "Find paths between two vertices" — this triggers a graph path-finding algorithm/query execution against the NebulaGraph database
Documented attack patterns abuse exactly the kind of access find_path 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_path:
{
"version": "1",
"default": "deny",
"tools": {
"find_path": {
"limits": [
{
"counter": "find_path_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}find_path stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find paths between two vertices. It is categorised as a Execute tool in the NebulaGraph MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the NebulaGraph MCP Server MCP server in PolicyLayer and add a rule for find_path: 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_path is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the find_path 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_path. 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_path 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.