Find concrete references to a symbol in indexed chunks. Returns total usageCount and top usage snippets.
AI agents call get_symbol_references to retrieve information from Codebase Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a search/query operation that returns read-only information about symbol usage patterns. It has no side effects, does not modify code, execute operations, or delete anything. The verb 'Find' and the action of returning usage statistics and snippets are purely informational retrieval activities typical of Read category tools.
From the tool's definition Tool name 'get_symbol_references' and description 'Find concrete references to a symbol in indexed chunks. Returns total usageCount and top usage snippets.' — this retrieves and queries existing codebase data without modifying anything.
Documented attack patterns abuse exactly the kind of access get_symbol_references gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Codebase Context, and nothing reaches the server without passing your rules. This is the rule we recommend for get_symbol_references:
{
"version": "1",
"default": "deny",
"tools": {
"get_symbol_references": {}
}
}get_symbol_references is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find concrete references to a symbol in indexed chunks. Returns total usageCount and top usage snippets. It is categorised as a Read tool in the Codebase Context MCP Server, which means it retrieves data without modifying state.
Register the Codebase Context MCP server in PolicyLayer and add a rule for get_symbol_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 Codebase Context. Nothing to install.
get_symbol_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 get_symbol_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 get_symbol_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.
get_symbol_references is provided by the Codebase Context MCP server (patricksys/codebase-context). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Codebase Context tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
11 Codebase Context tools catalogued and risk-classified — across an index of 42,500+ MCP servers.