Fetches code errors and issues for a specific file using the LSP textDocument/diagnostic API.
AI agents call get_errors 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 and returns diagnostic data about a file's errors and issues. It performs no data modification, deletion, code execution, or side effects—it only queries and returns information about the code's state. This is a classic Read operation with minimal security risk, appropriate for AI analysis tasks.
From the tool's definition Tool description states it 'Fetches code errors and issues' using the LSP diagnostic API. The verb 'Fetches' indicates retrieval without modification.
Documented attack patterns abuse exactly the kind of access get_errors 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 get_errors:
{
"version": "1",
"default": "deny",
"tools": {
"get_errors": {}
}
}get_errors 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.
Fetches code errors and issues for a specific file using the LSP textDocument/diagnostic API. 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 get_errors: 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.
get_errors 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_errors 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_errors. 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_errors 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.