Find non-declaration usages of a known identifier across the local codebase. Use this tool when you need to: - Locate call sites or consumers of a known function, class, or constant - Exclude declaration hits from identifier-style navigation - Narrow usage lookup with include_paths or exclude_paths
AI agents call symbol_references to retrieve information from Context Engine MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic search and analysis of an existing codebase to identify references to symbols. It retrieves information about where identifiers are used without modifying, executing, or deleting anything. The filtering parameters (include_paths, exclude_paths) support targeted querying rather than any state-changing operation.
From the tool's definition Tool description states 'Find non-declaration usages of a known identifier across the local codebase' and explicitly lists use cases as locating 'call sites or consumers' and performing 'identifier-style navigation' with filtering options.
Documented attack patterns abuse exactly the kind of access symbol_references gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Context Engine MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for symbol_references:
{
"version": "1",
"default": "deny",
"tools": {
"symbol_references": {}
}
}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 non-declaration usages of a known identifier across the local codebase. Use this tool when you need to: - Locate call sites or consumers of a known function, class, or constant - Exclude declaration hits from identifier-style navigation - Narrow usage lookup with include_paths or exclude_paths. It is categorised as a Read tool in the Context Engine MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Context Engine MCP Server MCP server in PolicyLayer and add a rule for 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 Context Engine MCP Server. Nothing to install.
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 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 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.
symbol_references is provided by the Context Engine MCP Server MCP server (kirachon/context-engine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Context Engine MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
50 Context Engine MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.