Get all diagnostics from the workspace
AI agents call get_all_diagnostics to retrieve information from Diagnostics MCP 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 diagnostic information from VS Code (linting errors, type issues, formatting problems, etc.). It has no side effects, cannot modify code or workspace state, cannot execute operations, and cannot delete or move data. It is purely informational retrieval, making it a Read category tool with low severity risk.
From the tool's definition Tool name 'get_all_diagnostics' and description 'Get all diagnostics from the workspace' indicate a retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
Get all diagnostics from the workspace. It is categorised as a Read tool in the Diagnostics MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Diagnostics MCP Server MCP server in PolicyLayer and add a rule for get_all_diagnostics: 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 Diagnostics MCP Server. Nothing to install.
get_all_diagnostics 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_all_diagnostics 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_all_diagnostics. 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_all_diagnostics is provided by the Diagnostics MCP Server MCP server (maaz0313-png/diagnostics-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →