MCP Diagnostics Extension

v1.0.0Developer Toolsstable

Exposes VS Code diagnostic problems like errors and warnings in real-time to AI agents via the Model Context Protocol. It enables AI tools to see compilation and linting issues directly from the problems panel to provide context-aware debugging and a

ai-agent-toolsai-toolsclean-architecturediagnostic-tooldiagnostics
Share:
22
Stars
0
Downloads
0
Weekly
0/5

What is MCP Diagnostics Extension?

MCP Diagnostics Extension is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to exposes vs code diagnostic problems like errors and warnings in real-time to ai agents via the model context protocol. it enables ai tools to see compilation and linting issues directly from the probl...

Exposes VS Code diagnostic problems like errors and warnings in real-time to AI agents via the Model Context Protocol. It enables AI tools to see compilation and linting issues directly from the problems panel to provide context-aware debugging and a

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Exposes VS Code diagnostic problems like errors and warnings

Use Cases

VS Code diagnostic exposure
Real-time error and warning access
IDE problem integration
newbpydev

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.0.0
UpdatedApr 5, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-diagnostics-extension

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP Diagnostics Extension

MCP Diagnostics Extension is a VS Code extension that bridges the IDE's built-in Problems panel with the Model Context Protocol, giving AI agents real-time read access to every compilation error, linting warning, and diagnostic message in your workspace. It exposes three MCP tools — getProblems for filtered workspace-wide diagnostics, getProblemsForFile for file-scoped errors, and getWorkspaceSummary for aggregate statistics — so AI coding assistants can see the same errors you see and provide context-aware fixes without you having to paste error messages manually.

Prerequisites

  • VS Code 1.96.0 or later
  • Node.js 22.x (for source builds or the bundled standalone MCP server)
  • An MCP-compatible AI client: Claude Desktop, Claude Code, Cursor, or any client that supports the MCP stdio transport
  • The extension installed from the VS Code Marketplace (publisher: newbpydev)
1

Install the extension from the VS Code Marketplace

Open VS Code, press Ctrl+Shift+X (Cmd+Shift+X on macOS), search for 'MCP Diagnostics Extension' by newbpydev, and click Install. The extension activates automatically on startup.

2

Verify the extension is active

After installation, look for the status bar item at the bottom of VS Code. It shows the current error and warning count in the format '$(bug) MCP: XE YW' with color coding: red for errors, orange for warnings, green for clean.

3

Locate the bundled MCP server script

The extension ships with a standalone MCP server script at scripts/mcp-server.js inside the extension installation directory. Find the path to use in your client config.

# On macOS, the extension is typically installed at:
# ~/.vscode/extensions/newbpydev.mcp-diagnostics-extension-*/scripts/mcp-server.js
ls ~/.vscode/extensions/newbpydev.mcp-diagnostics-extension-*/scripts/
4

Add the server to your MCP client config

Configure your MCP client to launch the bundled server script using Node.js. Set cwd to the extension directory so the script can find its dependencies.

{
  "mcpServers": {
    "vscode-diagnostics": {
      "command": "node",
      "args": ["scripts/mcp-server.js"],
      "cwd": "/Users/yourname/.vscode/extensions/newbpydev.mcp-diagnostics-extension-1.4.0",
      "env": {
        "NODE_ENV": "production",
        "MCP_DEBUG": "false"
      }
    }
  }
}
5

Use the automated setup command (alternative)

The extension includes a one-click setup command that auto-injects the MCP server configuration into detected client configs. Open the VS Code Command Palette and run the configure command.

# In VS Code Command Palette (Ctrl+Shift+P / Cmd+Shift+P):
# > MCP Diagnostics: Configure Server

MCP Diagnostics Extension Examples

Client configuration

MCP client config entry pointing to the standalone diagnostics server bundled with the VS Code extension.

{
  "mcpServers": {
    "vscode-diagnostics": {
      "command": "node",
      "args": ["scripts/mcp-server.js"],
      "cwd": "/Users/yourname/.vscode/extensions/newbpydev.mcp-diagnostics-extension-1.4.0",
      "env": {
        "NODE_ENV": "production",
        "MCP_DEBUG": "false"
      }
    }
  }
}

Prompts to try

Example prompts that ask the AI agent to use the diagnostic tools to help fix your code.

- "What errors and warnings are currently showing in my VS Code Problems panel?"
- "Get all TypeScript errors in src/auth/login.ts and suggest fixes"
- "Give me a workspace summary — how many errors and warnings are there and which files have the most?"
- "I just refactored the user service. Check the Problems panel and tell me what broke"
- "Fix all ESLint warnings in the current file"

Troubleshooting MCP Diagnostics Extension

MCP client shows the server as disconnected even though the extension is installed

The cwd path in your MCP config must point to the exact versioned extension directory. Run 'ls ~/.vscode/extensions/' to find the exact folder name including the version number, then update cwd accordingly. The extension directory name changes with each version.

getProblems returns an empty list even though VS Code shows errors in the Problems panel

The diagnostics server connects to VS Code's diagnostic API when VS Code is running. Make sure VS Code is open with a workspace and that the extension is showing in the status bar. If you recently installed the extension, reload the VS Code window (Ctrl+Shift+P > Developer: Reload Window) to activate it.

The automated 'MCP Diagnostics: Configure Server' command is not visible in the Command Palette

The command is only registered after the extension activates. Ensure VS Code has a folder or workspace open (the extension requires a workspace context to activate). Open a project folder and wait a few seconds, then try the Command Palette again.

Frequently Asked Questions about MCP Diagnostics Extension

What is MCP Diagnostics Extension?

MCP Diagnostics Extension is a Model Context Protocol (MCP) server that exposes vs code diagnostic problems like errors and warnings in real-time to ai agents via the model context protocol. it enables ai tools to see compilation and linting issues directly from the problems panel to provide context-aware debugging and a It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP Diagnostics Extension?

Follow the installation instructions on the MCP Diagnostics Extension GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MCP Diagnostics Extension?

MCP Diagnostics Extension works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP Diagnostics Extension free to use?

Yes, MCP Diagnostics Extension is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-diagnostics-extension": { "command": "npx", "args": ["-y", "mcp-diagnostics-extension"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MCP Diagnostics Extension?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides