MCP Diagnostics Extension MCP Server

Connect MCP Diagnostics Extension to Claude, Cursor or any other MCP client and it stops being a tab you switch to. A VS Code extension that exposes diagnostic information via Model Context Protocol (MCP) for AI agents. The mcp diagnostics extension mcp server is what makes that connection.

What the server does

The MCP Diagnostics Extension bridges VS Code's powerful diagnostic system with the Model Context Protocol, enabling AI agents to access your code problems in real-time. Whether you're debugging TypeScript errors, ESLint warnings, or custom linter issues, this extension makes all diagnostic information instantly available to your AI tools.

• 🤖 AI-First Development — Modern development increasingly relies on AI assistance. This extension ensures your AI tools have complete visibility into your codebase health
• ⚡ Real-time Integration — No more manually copying error messages or explaining problems to AI tools - they see everything instantly
• 🔧 Universal Diagnostics — Works with any VS Code diagnostic provider (TypeScript, ESLint, custom linters, etc.)
• 📊 Enhanced Productivity — AI agents can provide more contextual help when they understand your current problems

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

• getProblems — Get all diagnostics with filtering
• getProblemsForFile — Get problems for specific files
• getWorkspaceSummary — Get workspace-wide statistics
• File-by — file breakdown

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Credentials and setup notes

Configuration is passed through the environment: MCP_DEBUG. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Where it fits

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MCP Diagnostics Extension's toolset — getProblems, getProblemsForFile, getWorkspaceSummary and 1 more — is a fair guide to whether it matches your workflow. It is maintained by newbpydev; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Worth knowing first

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.