What does the vscode-ai-model-detector MCP Server do?

It provides real-time detection and classification of AI models used in GitHub Copilot and other AI-powered extensions within Visual Studio Code, identifying the current model, its vendor, family, and capabilities.

How many AI models does this extension support?

The extension supports 41+ model IDs across major AI providers through its dynamic model registry.

Which VS Code installations are compatible with this extension?

It works with VS Code Stable, Insiders, and VSCodium installations.

How does the extension detect AI models?

It uses direct integration with VS Code's SQLite storage and the Chat Participant API to access actual VS Code settings for high-confidence model detection.

MCP Connector

Detect AI Models in VS Code

Name: vscode-ai-model-detector MCP Server
Availability: OnlineOnly
Author: Romar J

AI model detector for VS Code. Identifies GitHub Copilot and other AI models in real-time using native storage. Supports 41+ models.

Connect

Works with vscodegithubcopilot

Romar J

Maintainer?

Spark score

out of 100

Updated 8 months ago

Fresher alternatives ↓

Version 2.1.0

Models

gpt 4gpt 4oclaude 3 5 sonnetclaude 3 5 haiku

Add to Favorites

Why it matters

Gain clarity on the AI models powering your VS Code environment. This extension accurately identifies and classifies AI models used by extensions like GitHub Copilot, providing insights into their family, vendor, and capabilities.

Outcomes

What it gets done

Real-time detection of active AI models within VS Code.

Classification of models by family, vendor, and capabilities.

Monitoring of AI model changes as they occur.

Support for various VS Code installations and AI providers.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-vscode-ai-model-detector | bash

Capabilities

Tools your agent gets

detect_ai_model

Detects the current AI model being used in VS Code with real-time accuracy.

monitor_model_changes

Monitors AI model changes in real-time with customizable intervals.

get_model_capabilities

Retrieves model capabilities and metadata for specific AI models.

identify_model_metadata

Identifies model family, vendor, token limits, and context windows.

Overview

vscode-ai-model-detector MCP Server

This is a VS Code extension that detects and classifies AI models used by other extensions, such as GitHub Copilot. It leverages VS Code's native storage for real-time identification and provides details about the model's family, vendor, and capabilities. It supports over 41 model IDs from major AI providers and works across different VS Code installations. This extension is useful for developers who want to understand which specific AI models are active in their VS Code environment. It helps in optimizing workflows and ensuring the intended AI tools are being utilized.

What it does

A Visual Studio Code extension that provides real-time detection and classification of AI models used in GitHub Copilot and other AI-powered extensions. Supports accurate model identification using VS Code's native storage and settings.

Features:

Real-Time Model Detection: Accurately identifies current AI model from VS Code's application storage
Dynamic Model Registry: Supports 41+ model IDs across major AI providers
High Performance: Direct integration with VS Code's SQLite storage
Comprehensive Classification: Detects model family, vendor, and capabilities
Live Updates: Monitor model changes in real-time
High Confidence Detection: Uses actual VS Code settings and Chat Participant API
Multi-Installation Support: Works with VS Code Stable, Insiders, and VSCodium

Example Usage:

const detector = vscode.extensions.getExtension('thisis-romar.vscode-ai-model-detector');
const api = await detector.activate();

const result = await api.detectCurrentModel();
console.log('Current Model:', result.currentModel);

Source README

VS Code AI Model Detector

Features

🔍 Real-Time Model Detection: Accurately identifies current AI model from VS Code's application storage
🧠 Dynamic Model Registry: Supports 41+ model IDs across major AI providers
⚡ High Performance: Direct integration with VS Code's SQLite storage
📊 Comprehensive Classification: Detects model family, vendor, and capabilities
🔄 Live Updates: Monitor model changes in real-time
🎯 High Confidence Detection: Uses actual VS Code settings and Chat Participant API
🛡️ Multi-Installation Support: Works with VS Code Stable, Insiders, and VSCodium

Supported Models

Source: Model IDs and formats match official VS Code Chat Model enums from microsoft/vscode-copilot-chat configurationService.ts

OpenAI GPT Series

GPT-4.1 (2025-04-14) (VS Code Chat Model)
GPT-4o mini (VS Code Chat Model)
GPT-5 (VS Code Chat Model)
GPT-5 mini (VS Code Chat Model)
GPT-5-Codex (VS Code Chat Model)

OpenAI O-Series

Anthropic Claude Series

Claude 3.5 Sonnet (VS Code Chat Model)
Claude 3.7 Sonnet (VS Code Chat Model)
Claude Haiku 4.5 (VS Code Chat Model)
Claude Opus 4 (VS Code Chat Model)
Claude Opus 4.1 (VS Code Chat Model)
Claude Sonnet 4 (VS Code Chat Model)
Claude Sonnet 4.5 (VS Code Chat Model)

Google Gemini Series

Gemini 2.5 Pro (VS Code Chat Model)
Gemini 2.0 Pro Experimental (VS Code Chat Model)
Gemini 2.0 Flash (VS Code Chat Model)

Other Models

DeepSeek Chat (VS Code Chat Model)
Grok Code Fast 1 (VS Code Chat Model)

Installation

Open VS Code
Go to Extensions (Ctrl+Shift+X)
Search for "AI Model Detector"
Click Install

Or install from VS Code Marketplace: AI Model Detector Extension

Usage

Basic Detection

const detector = vscode.extensions.getExtension('thisis-romar.vscode-ai-model-detector');
const api = await detector.activate();

const result = await api.detectCurrentModel();
console.log('Current Model:', result.currentModel);

Monitor Model Changes

// Start monitoring with 5 second intervals
const sessionId = await api.startModelMonitoring(5000);

// Later, stop monitoring
await api.stopModelMonitoring(sessionId);

Get Model Capabilities

const modelInfo = await api.getModelCapabilities('claude-3.5-sonnet');
console.log('Capabilities:', modelInfo.capabilities);

How It Works

Model Detection Process

Queries VS Code's SQLite storage database (state.vscdb)
Looks for chat.currentLanguageModel.panel key
Parses model identifier to determine family and provider
Cross-references with dynamic registry of 41+ models
Returns comprehensive model information with high confidence

Dynamic Registry

Real-time updates for new model versions
Format normalization (dots vs hyphens)
Comprehensive metadata including:
- Token limits
- Special capabilities
- Context windows
- Model families
- Vendor information

Model Metadata

Each detected model includes:

interface ModelInfo {
  id: string;           // Unique model identifier
  name: string;         // Display name
  vendor: ModelVendor;  // OpenAI, Anthropic, Google, etc.
  family: ModelFamily;  // GPT, Claude, Gemini, etc.
  maxTokens: number;    // Maximum context length
  capabilities: ModelCapability[]; // Supported features
  version?: string;     // Model version if available
  accuracy?: string;    // Detection accuracy level
}

Configuration

No configuration required for basic usage. The extension automatically detects models from VS Code's native storage.

Requirements

Visual Studio Code >= 1.85.0
GitHub Copilot extension (for Copilot model detection)
Active AI extension using VS Code's Chat Participant API

Attribution

This project follows the GIT-ATT-001 v1.1.0 standard for AI attribution. All commits should include proper AI attribution blocks:

AI-Attribution:
- Model: <model-id> (Vendor)
- Session: <chat-session-uuid or manual-commit-timestamp>
- Context: <development context>

Co-authored-by: <Platform-Name> (<model-id>) <admin+llm-[normalized-id]@emblemprojects.com>

FAQ

Common questions

Discussion