Reads a symbol (function, class, method, etc.) by name and type in a given file using LSP.
AI agents call read_symbol 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.
This tool retrieves code structure information (functions, classes, methods) without modifying any data. It is a query/lookup operation against code, analogous to searching or fetching. The read-only nature is confirmed by the existence of separate write and edit tools on the same server. No side effects, data modification, code execution, or destructive actions are possible.
From the tool's definition Tool name is 'read_symbol' and description states it 'Reads a symbol...using LSP' with no modification capability; sibling tools include 'write_file' and 'edit_symbol' which are separate, confirming this one is read-only.
Documented attack patterns abuse exactly the kind of access read_symbol 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 read_symbol:
{
"version": "1",
"default": "deny",
"tools": {
"read_symbol": {}
}
}read_symbol 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.
Reads a symbol (function, class, method, 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 read_symbol: 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.
read_symbol 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 read_symbol 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 read_symbol. 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.
read_symbol 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.