Finds all references to a symbol (function, class, etc.) by name and type in a given file using LSP.
AI agents call find_references to retrieve information from Vsc 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 to retrieve references within code without altering any data. This is purely informational analysis—no code is created, modified, deleted, or executed. It falls squarely into the Read category with low severity since discovering symbol references poses minimal risk even if misused by an agent.
From the tool's definition Tool 'finds all references to a symbol' with no modification capability; returns data about symbol usage locations via LSP query functionality.
Documented attack patterns abuse exactly the kind of access find_references gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Vsc, and nothing reaches the server without passing your rules. This is the rule we recommend for find_references:
{
"version": "1",
"default": "deny",
"tools": {
"find_references": {}
}
}find_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.
Finds all references to a symbol (function, class, etc.) by name and type in a given file using LSP. It is categorised as a Read tool in the Vsc MCP Server, which means it retrieves data without modifying state.
Register the Vsc 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 Vsc. 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 Vsc MCP server (thomasgazzoni/vsc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Vsc tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 Vsc tools catalogued and risk-classified — across an index of 42,500+ MCP servers.