Locates all usages and references of a symbol throughout the codebase.
AI agents call references to retrieve information from MCP Language Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves reference locations for a symbol across the codebase without modifying, executing, or deleting anything. It is a pure read/search operation with minimal blast radius.
From the tool's definition Locates all usages and references of a symbol throughout the codebase
Documented attack patterns abuse exactly the kind of access references gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Language Server, and nothing reaches the server without passing your rules. This is the rule we recommend for references:
{
"version": "1",
"default": "deny",
"tools": {
"references": {}
}
}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.
Locates all usages and references of a symbol throughout the codebase. It is categorised as a Read tool in the MCP Language Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Language Server MCP server in PolicyLayer and add a rule for 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 MCP Language Server. Nothing to install.
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 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 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.
references is provided by the MCP Language Server MCP server (isaacphi/mcp-language-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Language 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.
6 MCP Language Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.