AI agents call get_neighbors to retrieve information from Knocoph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a pre-built knowledge graph to retrieve relationship information about code symbols. It performs navigation and inspection only—no data is created, modified, deleted, or executed. The operation is deterministic and side-effect-free, fitting squarely within the Read category. The low severity reflects that extracting code structure information poses minimal risk even if misused by an agent.
From the tool's definition Tool description states 'Return one-hop neighbors' and 'Shows what a symbol calls, what calls it, what it imports, and what it extends.' These are all read-only graph traversal operations that retrieve existing structural relationships without modifying data.
Attacks that exploit this kind of access
Return one-hop neighbors of a known node. Shows what a symbol calls, what calls it, what it imports, and what it extends. It is categorised as a Read tool in the Knocoph MCP Server, which means it retrieves data without modifying state.
Register the Knocoph MCP server in PolicyLayer and add a rule for get_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 Knocoph. Nothing to install.
get_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 get_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 get_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.
get_neighbors is provided by the Knocoph MCP server (jagonzalr/knocoph). 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 →