AI agents call find_references to retrieve information from Graphdb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and returns information about where a given name is referenced in code. It has no side effects, does not execute code, does not modify data, and does not delete anything. It is purely an informational lookup, consistent with the 'Read' category for retrieval and query operations.
From the tool's definition Tool description states it finds 'inbound references to `name` (calls, imports, inheritance)' — a read-only query operation that retrieves code references without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
All inbound references to name (calls, imports, inheritance). It is categorised as a Read tool in the Graphdb MCP Server, which means it retrieves data without modifying state.
Register the Graphdb MCP server in PolicyLayer and add a rule for find_references: 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 Graphdb. Nothing to install.
find_references 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_references 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_references. 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_references is provided by the Graphdb MCP server (samagra001/claude-code-graphdb). 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 →