AI agents call find_nodes to retrieve information from Sfgraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
find_nodes retrieves or searches for nodes in the knowledge graph based on glob-pattern matching. This is a read-only operation that queries existing data without side effects, aligning with the Read category (search, list, get, fetch). The low severity reflects that pattern-based lookups cannot cause harm to data integrity or system state.
From the tool's definition Tool performs 'node lookup' with pattern matching against node qualifiedName; described as a querying/retrieval operation with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Glob-pattern node lookup. Pattern matches node qualifiedName with. It is categorised as a Read tool in the Sfgraph MCP Server, which means it retrieves data without modifying state.
Register the Sfgraph MCP server in PolicyLayer and add a rule for find_nodes: 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 Sfgraph. Nothing to install.
find_nodes 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_nodes 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_nodes. 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_nodes is provided by the Sfgraph MCP server (ryanstark24/sfgraph). 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 →