Find all references to a symbol (class, function, variable) across the codebase.
AI agents call find_references to retrieve information from Ue Codegraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a local SQLite database to locate references to code symbols. It is a read-only operation analogous to grep or IDE symbol search. The severity is low because even if an attacker queries references to arbitrary symbols, no code is executed, no data is modified, and no damage can occur—only information is retrieved.
From the tool's definition Tool name 'find_references' and description 'Find all references to a symbol (class, function, variable) across the codebase' indicate a query/search operation that retrieves information without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Find all references to a symbol (class, function, variable) across the codebase. It is categorised as a Read tool in the Ue Codegraph MCP Server, which means it retrieves data without modifying state.
Register the Ue Codegraph 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 Ue Codegraph. 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 Ue Codegraph MCP server (yomenstyle/ue-codegraph-mcp). 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 →